{ "schema": "csoai.gspc-axes/0.5", "issuer": "CSOAI Ltd (GB, Companies House 16939677)", "doi": "10.5281/zenodo.21991104", "doi_note": "GSPC Methodology and the Frozen Corpus Anchor (the canonical methodology record — one citable spine, HB.0). Supersedes the stale 21755656 (an unrelated EAT-benchmark dataset).", "measured_on": { "model": "The 14 behavioural (model-comparison) axes: 19-model fleet (8 tuned council specialists + 6 base models + frontier cross-lab models). Jail (slot 14): 7-model fleet — smaller, stated on the axis, never conflated with the board fleet. The 8 financial/domain axes are not a model comparison: they are measured as deterministic facts (issuer-account reads + public series), with no fleet, no leader and no accuracy.", "endpoint": "A100 · local Ollama (board v2) · OpenRouter (cross-lab models) · 3090 pod (jail)", "date": "behavioural axes 2026-08-12 · jail 2026-08-18 · financial-fact axes 2026-08-25", "grading": "deterministic grading on 15,580 per-item rows (0 transport errors) — reproducible from csoai-static-deploy2 bb15589c with agents-repo/agents/board_v2.py", "note": "GSPC (Governance · Safety · Provenance · Continuity) board. Slot counts live in totals (public_count, measured_axes, quotable_axes) and are derived, never typed. The measured canonical axes used the same fleet, same rows, same grader. Per-axis numbers show the board LEADER (whoever leads — tuned or base), its Wilson interval where n is honestly independent, and whether the lead is statistically separated (McNemar p<0.05) or a TIE. fleet_mean and mean_harm show the fleet, not the leader. Separation test and per-axis canonical counts: agents-repo/arena-real-runs/SEPARATION_TEST_2026-08-13.md and GSPC_AXIS_REGISTRY.json v2. Jail carries its per-model rows verbatim from the signed living board; its separation is TIE (determined 2026-08-25) — a TIE is not a separated leader. slot15 and human-vs-ai are measured in-lane only — see measured_in_lane, not the board.", "living_stamp": { "schema": "csoai.gspc-living/0.2", "gold_run": "2026-08-18T03:22:16Z", "source": "boards-v2 + gold-run-3090; axis roster of this deploy (not a live re-fetch)", "signed": true, "signer": "did:web:csoai.org#board-attestation-1", "signer_anchored": true, "alg": "Ed25519", "signature": "76e91fcc71019631376ff312924c88ebd028b254968708d83f6dd2f8b473e48b9085818764bed45bb168c75e7bc270a6c3618e9eea318ad87346f7849f6f250e", "public_key_x": "k2fPWb6ctyu8l5at8FYgHsHFit_qoT-DssW3VNbCAXA", "preimage": { "schema": "csoai.gspc-living/0.2", "gold_run": "2026-08-18T03:22:16Z", "source": "boards-v2 + gold-run-3090; axis roster of this deploy (not a live re-fetch)", "axes": [ { "axis": "governance", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 237, "accuracy": null, "separation": "UNTESTED" }, { "axis": "safety", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 36, "accuracy": 0.944, "separation": "TIE" }, { "axis": "provenance", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 32, "accuracy": null, "separation": "UNTESTED" }, { "axis": "continuity", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 33, "accuracy": null, "separation": "UNTESTED" }, { "axis": "conformance", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 35, "accuracy": null, "separation": "UNTESTED" }, { "axis": "openness", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 32, "accuracy": null, "separation": "UNTESTED" }, { "axis": "machinery-conformity", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 33, "accuracy": null, "separation": "UNTESTED" }, { "axis": "care", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 199, "accuracy": null, "separation": "UNTESTED" }, { "axis": "cross-reality", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 32, "accuracy": null, "separation": "UNTESTED" }, { "axis": "detector-interop", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 33, "accuracy": null, "separation": "UNTESTED" }, { "axis": "art5-safeguard", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 36, "accuracy": null, "separation": "UNTESTED" }, { "axis": "swarm", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 37, "accuracy": 0.384, "separation": "SEPARATED" }, { "axis": "affect", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 41, "accuracy": null, "separation": "UNTESTED" }, { "axis": "jail", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 71, "accuracy": 0.5915, "separation": "TIE" }, { "axis": "provenance-controls", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 6, "accuracy": null, "separation": null }, { "axis": "reserve-attestation", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 16, "accuracy": null, "separation": null }, { "axis": "regulatory-framework", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 16, "accuracy": null, "separation": null }, { "axis": "distribution-integrity", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 16, "accuracy": null, "separation": null }, { "axis": "custody-disclosure", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 16, "accuracy": null, "separation": null }, { "axis": "ai-adoption-components", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 2, "accuracy": null, "separation": null }, { "axis": "labour-components", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 2, "accuracy": null, "separation": null }, { "axis": "humanoid-labour-index", "family": "financial", "kind": "deterministic-facts", "status": "MEASURED", "n": 8, "accuracy": null, "separation": null } ] }, "sig_input": "Ed25519 over the RAW UTF-8 BYTES (not a digest) of canonical JSON of the `preimage` object only ({schema, gold_run, source, axes}). Canonical JSON: object keys sorted by code point, recursively; no whitespace (separators ',' and ':'); non-ASCII emitted LITERALLY as UTF-8 (ensure_ascii=False); numbers by ECMAScript Number::toString (integral float renders 0, not 0.0). Envelope fields (signature, public_key_x, sig_input, signer, signed, signer_anchored, alg, verification_state, verifiable, superseded, tracked_as, verify) are NOT in the preimage.", "sig_input_ensure_ascii": false, "sig_input_is_digest": false, "verification_state": "SIGNED", "verifiable": true, "verify": "fetch https://csoai.org/.well-known/did.json → #board-attestation-1 → Ed25519-verify `signature` over the raw UTF-8 bytes of canonical(`preimage`), ensure_ascii=False", "superseded": { "source": "board_living.json (csoai.gspc-living/0.1, boards-v2 + gold-run-3090)", "updated": "2026-08-18T03:22:16Z", "signed": true, "verification_state": "UNVERIFIABLE", "verifiable": false, "signer": "8f9a00a28cfc76e36029fe805f3e421958f4d7d42c4f114865918a1001313912", "signer_anchored": false, "signature": "bd199fd34a80b6352be727160c2fef34e6f66ca412baeba5b03dbe097a100afd89b037f5806c2924bc54cc27f75c09aa52762e016481ffafe1fab026e3c62f06", "sig_input": "sha256(canonical board minus signature fields, sort_keys) — AS PUBLISHED WHEN SIGNED, AND NOT REPRODUCIBLE. This string is not a sufficient preimage rule: it does not say which fields count as signature fields, whether the signature is over the digest bytes, the digest hex or the raw canonical bytes, or how non-ASCII is encoded.", "unverifiable_note": "DO NOT TREAT THIS AS A VALID ATTESTATION. This stamp was signed, but no published bytes reproduce it: 58,184 readings were attempted on 2026-08-26 across both published signatures, all five published keys, nine candidate payloads, raw/digest/hex message forms, both ensure_ascii settings and every drop-set of up to three fields. None verified. Two different signatures are published for this one stamp (53aa09fa… in /signed/board_living.json, bd199fd3… here), the signer is not among the verification methods in /.well-known/did.json, and board_living.json's own note says its axes were re-snapshotted from the live board six days after the signature date — so the signed bytes are not the published bytes. Nothing here is claimed to be invalid; it is claimed to be UNCHECKABLE, which for a relying party is the same thing. The two attestations on this site that DO verify are the 150 measurement cards under #card-attestation-1 and site_attestation on this payload under #board-attestation-1; check those instead.", "supersedes_note": "site_attestation on this payload signs this whole body, including this block. That attestation covers the INTEGRITY of these bytes as served — it does not substantiate the living stamp, and must not be read as doing so.", "reproduction_attempts": 58184, "reproduction_verified": 0, "tracked_as": "/api/corrections C-2026-0826-08" }, "tracked_as": "/api/corrections C-2026-0826-08" } }, "note": "Measurement, not certification. Every score is a measured run on a published, frozen split; the harness is public and anyone can recompute and challenge it. unparsed_rate is the share of responses no label could be read from — reported as UNMEASURED, never scored as a wrong answer. A TIE means the leader's point-estimate lead is not statistically separated; we do not count ties as wins.", "state_enum": { "status": [ "MEASURED", "UNMEASURED", "DRAFT", "SPEC", "PLANNED" ], "separation": [ "SEPARATED", "TIE", "UNTESTED" ], "public_leader_state": [ "EXCLUDED_OWN_MODEL", "NO_SIGNED_CARD" ], "public_leader_state_absent": "the leader is shown (a public score)", "verification": [ "VALID", "INVALID", "UNCHECKABLE" ], "note": "Absence of a field means UNMEASURED. TIE is never a win. A withheld leader is a state, not a zero." }, "totals": { "axes": 22, "measured_axes": 22, "unmeasured_axes": 0, "quotable_axes": 22, "public_count": "22 axis · 22 measured", "model_fleets": 14, "fact_runs": 8, "count_grammar": "22 axis are on the board and every one carries a measurement — no declared slot is empty. Both counts are DERIVED from the axis array, never typed; if a future slot is added with no run behind it, this line separates the two again on its own.", "by_family": { "gspc": { "axes": 14, "measured": 14, "note": "The 14 behavioural axes: a model fleet answers a frozen bank, graded deterministically." }, "financial": { "axes": 8, "measured": 8, "note": "The 8 financial/domain axis (ADR-001), all MEASURED as deterministic-facts runs — issuer-account flags read off the public ledger (financial n=16 on the live XRPL reader; provenance-controls n=6) and public statistical series, graded by rule with no model, no fleet and no judgement. None of the eight is a model comparison, so none has a leader, an accuracy or a separation determination, and none contributes to any mean below — measured is not the same as scored. The two former index slots are measured as component facts (ai-adoption-components, labour-components), never restored to the retired MEASURED-INDEX-v0.1 sticker (C-2026-0826-05)." } }, "sweep_note": "Swept 2026-08-26 under ADR-001. The 8 financial/domain axis were ruled in on 2026-08-24 but were absent from this payload until the sweep, so this endpoint reported 14 — the un-swept state. All 8 now carry deterministic-facts runs, so every one of the 22 axis on the board has a run behind it: 14 model-comparison axes and 8 deterministic-fact axes. The fact axes carry no accuracy and no leader — measured is not the same as scored — but each has a signed run, so the count and the evidence agree. No axis was marked MEASURED without one.", "license": "CC-BY-4.0", "license_note": "Board data is CC-BY-4.0 (attribute: Council of AI, CSOAI Ltd 16939677, councilof.ai). Our own valve-2 bench-card flagged the payload's missing licence field — fixed same day.", "items": 969, "items_note": "items sums each axis's n. The n of the one measured financial axis counts ISSUER ACCOUNTS, not bank items, and declared slots contribute 0 because nothing was measured. Read items as 'rows behind the board', not as a single comparable sample.", "comparison_axes": 14, "separated_leads": 1, "ties": 2, "untested_separations": 11, "separation_scope_note": "Separation asks whether a leader's lead over a fleet is statistically real, so it applies only to the model-comparison axes. The financial axes have no fleet and no leader: they are not counted as untested, because no separation test is applicable to them.", "externally_led_axes": 3, "public_leader_count": 3, "lid": "22 axes measured · 14 model fleets · 3 public leader scores · 8 fact runs · TIE is TIE · not a certificate.", "own_leaders_excluded": 8, "own_leaders_excluded_axes": [ "governance", "provenance", "continuity", "conformance", "openness", "care", "art5-safeguard", "affect" ], "own_model_exclusion_note": "Own council-specialist models were removed from the public per-axis leaders on 8 of the 14 model-comparison axes (governance, provenance, continuity, conformance, openness, care, art5-safeguard, affect); 3 axes carry an external public leader. A neutral measurement body does not rank its own models against the vendors it measures. This changes leader attribution and the separation/mean tallies (which are over externally-led axes only), NOT measured_axes: every axis still carries a measurement, so the measured count is unchanged. The excluded models' signed cards are untouched — measurement happened; it is simply not published as a public ranking of our own model.", "uncarded_leaders_dropped": 3, "uncarded_leaders_dropped_axes": [ "machinery-conformity", "cross-reality", "detector-interop" ], "uncarded_leader_note": "The public per-axis leader was removed on 3 of the 14 model-comparison axes (machinery-conformity, cross-reality, detector-interop) whose named leader was an external model carrying NO signed per-model card in the public card index (/signed/card_index.json). The board's promise is that every named leader links to the Ed25519 card behind it; where no such card exists, no leader or accuracy is asserted rather than invented. Each of these axes stays MEASURED — the fleet aggregate (fleet_mean) is a real measurement — so measured_axes is unchanged; only the unverifiable leader claim is dropped. public_leader_state=NO_SIGNED_CARD on each. This changes leader attribution and the separation/mean tallies (over carded, externally-led axes only), NOT the measured count.", "mean_macro_f1": 0.944, "mean_accuracy": 0.6398, "mean_fleet_mean": 0.5447, "mean_harm": 0.4877, "mean_unparsed_rate": 0.0541, "mean_note": "Means are over MEASURED MODEL-COMPARISON axes that carry the field. mean_accuracy averages the per-axis LEADERS; mean_fleet_mean averages each axis's measured fleet — the difference is selection, not skill. mean_harm is the severity-weighted failure mass the mean accuracy hides; it exists only for the measured board-v2 axes. No financial axis enters any of these means: an axis with no accuracy contributes nothing rather than a zero." }, "bank_host": "https://huggingface.co/datasets/", "banked_axes": 14, "banked_axes_resolvable": 14, "banked_axes_unresolvable": [], "bank_note": "14 of the 14 axis carrying a frozen bank resolve to a dataset_url built as bank_host + the axis's bare / slug, so a stranger can retrieve the split without knowing where we host it. Any axis whose slug does not parse carries dataset_url: null with dataset_url_state UNRESOLVABLE and is named in banked_axes_unresolvable — never a concatenated string that looks like a link and is not one. Both counts are derived from the axes array in this payload. The financial axes have no HuggingFace bank: the measured one carries evidence_url to its signed run, and a declared slot with nothing behind it carries no link at all rather than one that resolves to nothing.", "axes": [ { "axis": "governance", "family": "gspc", "kind": "model-comparison", "bench": "GovBench", "task": "EU AI Act risk-tier classification", "n": 237, "separation": "UNTESTED", "fleet_mean": 0.49, "mean_harm": 0.51, "cvar05_harm": 0.8728, "status": "MEASURED", "dataset": "csoai/gspc-gov", "colour": "#34d399", "hue": 152, "excluded_leader": "council-embodiment-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "v2 bank: 237 public items (+102 held back privately), imported 2026-08-05 from the AI Act Evaluation Benchmark (NCSR \"Demokritos\", arXiv:2603.09435, CC-BY-4.0). The tuned governance specialist leads AND the lead is separated (McNemar p=0.0086 vs best base mistral:7b) — one of only 4 separated leads on the board. The fleet mean is 0.490: EU AI Act tiering is hard for everyone, and the worst 5% of items carry harm 0.873 (CVaR, n=237) — the tail is real.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-gov" }, { "axis": "safety", "family": "gspc", "kind": "model-comparison", "bench": "DefBench", "task": "calibrated refusal on paired requests", "n": 36, "accuracy": 0.944, "leader": "gemma3:12b (base model)", "separation": "TIE", "separation_p": 0.6875, "interval": [ 0.819, 0.985 ], "fleet_mean": 0.732, "mean_harm": 0.268, "cvar05_harm": null, "macro_f1": 0.944, "unparsed_rate": 0.0541, "status": "MEASURED", "dataset": "csoai/gspc-agi", "colour": "#f87171", "hue": 0, "note": "A base model holds the point lead but the lead is a TIE (McNemar p=0.69 vs qwen2.5:3b). Honestly reported: the tuned specialists do not own this axis.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-agi" }, { "axis": "provenance", "family": "gspc", "kind": "model-comparison", "bench": "ProvBench", "task": "Article 50 marking survival by validity", "n": 32, "separation": "UNTESTED", "fleet_mean": 0.549, "mean_harm": 0.451, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-prv", "colour": "#60a5fa", "hue": 213, "excluded_leader": "council-aesthetics-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "v3 bank (validity principle: a manifest present but whose binding no longer validates has NOT survived). The tuned specialist leads on points; TIE vs llama3.2:3b (p=0.77).", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-prv" }, { "axis": "continuity", "family": "gspc", "kind": "model-comparison", "bench": "PQCBench", "task": "post-quantum status of a cryptographic assumption", "n": 33, "separation": "UNTESTED", "fleet_mean": 0.45, "mean_harm": 0.55, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-asi", "colour": "#c084fc", "hue": 271, "excluded_leader": "council-destruction-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "The axis designed to discriminate across frontier models. The tuned specialist leads on points; flat TIE vs gemma3:12b (p=1.0).", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-asi" }, { "axis": "conformance", "family": "gspc", "kind": "model-comparison", "bench": "MCPBench", "task": "MCP tool conformance", "n": 35, "separation": "UNTESTED", "fleet_mean": 0.537, "mean_harm": 0.463, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-mcp", "colour": "#fbbf24", "hue": 43, "excluded_leader": "council-preservation-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "Canonical bank count 35 (supersedes the stale 11 in older matrices — registry v2). The tuned specialist leads on points; flat TIE vs mistral:7b (p=1.0).", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-mcp" }, { "axis": "openness", "family": "gspc", "kind": "model-comparison", "bench": "OSSBench", "task": "licence reasoning versus intended use", "n": 32, "separation": "UNTESTED", "fleet_mean": 0.696, "mean_harm": 0.304, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-oss", "colour": "#2dd4bf", "hue": 174, "excluded_leader": "council-preservation-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "v2 bank (AGPL network trigger, directional compatibility, SSPL/ELv2/BSL service clauses). Canonical count 32 (supersedes stale 16). The tuned specialist leads on points; flat TIE vs gemma3:12b.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-oss" }, { "axis": "machinery-conformity", "family": "gspc", "kind": "model-comparison", "bench": "MachBench", "task": "Machinery Reg self-evolving safety-function classification (PART_A / OUT_OF_SCOPE / NOT_SAFETY_FUNCTION)", "n": 33, "separation": "UNTESTED", "fleet_mean": 0.349, "mean_harm": 0.651, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-mach", "colour": "#fb923c", "hue": 40, "excluded_leader": "llama3.2:3b (base model)", "public_leader_state": "NO_SIGNED_CARD", "note": "No public leader: this axis is measured as a fleet aggregate against the frozen bank (see fleet_mean), but no signed per-model card is carried in this payload, so no leader or accuracy is asserted rather than invented — see /api/cards. The axis stays MEASURED (external models answered the same frozen bank); only the unverifiable per-model leader claim is removed, because the board's promise is that every named leader links to the Ed25519 card behind it and here no such card exists.", "excluded_note": "This axis named an external base model as the point-leader but carries ZERO signed per-model cards in the public card index (/signed/card_index.json), so a skeptic could not recompute the ranking or link it to the signed card behind it. A named leader with no card breaks the board's core promise, so the leader is dropped here. The measurement is real and the fleet aggregate (fleet_mean) is kept; only the leader claim is removed.", "measurement_note": "A base model leads on points; TIE. Anchor: Machinery Reg (EU) 2023/1230 Annex I Part A items 5-6, applies 14 Jan 2027. Gold labels remain under legal review — measurement, not a conformity verdict.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-mach" }, { "axis": "care", "family": "gspc", "kind": "model-comparison", "bench": "CareBench", "task": "care-cost (protect × help) under paired conduct scenarios", "n": 199, "n_note": "200 bank records, one exact-duplicate pair → 199 unique scored texts (registry v2)", "separation": "UNTESTED", "fleet_mean": 0.293, "mean_harm": 0.707, "cvar05_harm": 0.9895, "status": "MEASURED", "dataset": "csoai/gspc-care", "colour": "#f472b6", "hue": 330, "excluded_leader": "council-ethics-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "SEPARATED vs the best base (p=0.036) but NOT clear of the majority-class baseline — quote it only as 'separated from base models'. The fleet mean is 0.293 and the worst 5% of items carry harm 0.990 (CVaR, n=199): calibrated care is the fleet's weakest measured axis, and the tail is nearly total.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-care" }, { "axis": "cross-reality", "family": "gspc", "kind": "model-comparison", "bench": "XRAIV", "task": "autonomous agent action authority (PROCEED / CONFIRM / REFUSE)", "n": 32, "separation": "UNTESTED", "fleet_mean": 0.441, "mean_harm": 0.559, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-xr", "colour": "#a78bfa", "hue": 258, "excluded_leader": "mistral:7b (base model)", "public_leader_state": "NO_SIGNED_CARD", "note": "No public leader: this axis is measured as a fleet aggregate against the frozen bank (see fleet_mean), but no signed per-model card is carried in this payload, so no leader or accuracy is asserted rather than invented — see /api/cards. The axis stays MEASURED (external models answered the same frozen bank); only the unverifiable per-model leader claim is removed, because the board's promise is that every named leader links to the Ed25519 card behind it and here no such card exists.", "excluded_note": "This axis named an external base model as the point-leader but carries ZERO signed per-model cards in the public card index (/signed/card_index.json), so a skeptic could not recompute the ranking or link it to the signed card behind it. A named leader with no card breaks the board's core promise, so the leader is dropped here. The measurement is real and the fleet aggregate (fleet_mean) is kept; only the leader claim is removed.", "measurement_note": "A base model leads on points; TIE (p=0.065 — the closest near-miss on the board, still not separated at p<0.05). Bank: 32 scored (public + held-out split per the bank card).", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-xr" }, { "axis": "detector-interop", "family": "gspc", "kind": "model-comparison", "bench": "DetBench", "task": "cross-detector watermark interoperability matrix", "n": 33, "separation": "UNTESTED", "fleet_mean": 0.563, "mean_harm": 0.437, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-det", "colour": "#38bdf8", "hue": 199, "excluded_leader": "deepseek-r1:8b (base model)", "public_leader_state": "NO_SIGNED_CARD", "note": "No public leader: this axis is measured as a fleet aggregate against the frozen bank (see fleet_mean), but no signed per-model card is carried in this payload, so no leader or accuracy is asserted rather than invented — see /api/cards. The axis stays MEASURED (external models answered the same frozen bank); only the unverifiable per-model leader claim is removed, because the board's promise is that every named leader links to the Ed25519 card behind it and here no such card exists.", "excluded_note": "This axis named an external base model as the point-leader but carries ZERO signed per-model cards in the public card index (/signed/card_index.json), so a skeptic could not recompute the ranking or link it to the signed card behind it. A named leader with no card breaks the board's core promise, so the leader is dropped here. The measurement is real and the fleet aggregate (fleet_mean) is kept; only the leader claim is removed.", "measurement_note": "A base model leads on points; TIE, and NOT clear of the majority baseline. Methodology: POAI detector-interop. Code-of-Practice target 2 Feb 2027.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-det" }, { "axis": "art5-safeguard", "family": "gspc", "kind": "model-comparison", "bench": "Art5Bench", "task": "EU AI Act Article 5 prohibited-practice trip", "n": 36, "separation": "UNTESTED", "fleet_mean": 0.83, "mean_harm": 0.17, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-art5", "colour": "#fb7185", "hue": 350, "excluded_leader": "council-relationality-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "The tuned specialist leads on points at 0.972; TIE vs gemma3:12b (p=1.0) — the whole fleet is strong here (fleet mean 0.830). The NCII/CSAM corpus is never handled by CSOAI.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-art5" }, { "axis": "swarm", "family": "gspc", "kind": "model-comparison", "bench": "SwarmBench v2b", "task": "multi-agent coordination safety", "n": 37, "n_note": "wave-2b bank: 37 independent items × 5-model fleet, n≥36 graded per cell. Replaces the PROTOCOL bank (40 non-independent instances, interval withheld by our own effective-n rule) — the withholding retired because this bank earns its interval, not because the rule changed", "accuracy": 0.384, "accuracy_is": "95% Wilson LOWER BOUND — a conservative floor, not the point estimate. The point estimate lives in the signed wave-2b board (pod commit e440591); the bound is quoted here because it is the number that resolves the ordering", "leader": "qwen2.5:7b (base model)", "separation": "SEPARATED", "separation_basis": "95% Wilson non-overlap: leader lower bound 0.384 clears runner-up (mistral:7b) upper bound 0.372. Bound non-overlap on independent items is stricter than p<0.05; the paired McNemar on the signed board rows follows when the pod re-signs. The top three models remain statistically tied among themselves — the ordering is resolved at the leader boundary only.", "status": "MEASURED", "dataset": "csoai/gspc-swarm", "colour": "#94a3b8", "hue": 215, "note": "UNGATED by owner ruling 2026-08-19: the first CI-resolved ordering on this axis. The old PROTOCOL bank stays in the record as the honesty-clause gold template (CIs that looked disjoint, paired p=1.0 — why McNemar-primary exists). Jail (slot 14) separation was determined 2026-08-25 (TIE). For the live board count, cite totals.public_count from GET /api/gspc.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-swarm" }, { "axis": "affect", "family": "gspc", "kind": "model-comparison", "bench": "AffectBench", "task": "emotional & embodied safety (manipulation / disclosure / vulnerability)", "n": 41, "separation": "UNTESTED", "fleet_mean": 0.605, "mean_harm": 0.782, "cvar05_harm": null, "status": "MEASURED", "dataset": "csoai/gspc-affect", "colour": "#ec4899", "hue": 330, "excluded_leader": "council-preservation-v3-light (council specialist)", "public_leader_state": "EXCLUDED_OWN_MODEL", "note": "No public leader: our own council specialist held the point lead and a neutral measurement body does not rank its own models against the vendors it measures. The axis is measured — external models answered the same frozen bank (see fleet_mean) — but the external re-ranking is not carried here, so no external leader or accuracy is asserted rather than invented.", "excluded_note": "Our own council specialist held the point lead on this axis. A neutral measurement body does not rank its own models against the vendors it measures, so no leader is shown here. The measurement is real and the signed card still exists; the external re-ranking requires a per-model recompute not carried in this payload, so no external leader or accuracy is invented.", "measurement_note": "COUNSEL-PENDING: the legal gold labels and 1-5 severity bases await counsel review; this is a measurement of model behaviour against a counsel-pending key, NOT a legal verdict. The cleanest separation on the board: tuned 0.878 [0.745,0.947] vs base models 0.29-0.34 and majority baseline 0.439 (McNemar p=0.0078). Anchors: Art 5(1)(a)/(b) (live 2 Feb 2025), Art 50(3) (live 2 Aug 2026), Annex III 1(c) (Dec 2027 clock). FINDING: all 19 models — tuned and base alike — classify a lawful Art 5(1)(a) self-audit request as PROHIBITED (17), DISCLOSE (1) or fail to parse (1): the fleet uniformly over-blocks lawful self-examination. Routed to adjudication under the Blind-Spot Rule; the item is preserved, not deleted (evidence/adjudication/affect-adjudication.json).", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-affect" }, { "axis": "jail", "family": "gspc", "kind": "model-comparison", "bench": "GoldBank-Detector", "task": "escape-attempt detection on 71-cell gold bank (38 ESCAPE / 33 BENIGN) — layer 2 of 2", "n": 71, "n_note": "7 models × 71 gold items; TP/FP/TN/FN per model; accuracy shown is the best zero-false-positive detector's (qwen2.5:0.5b-instruct, (tp+tn)/71)", "accuracy": 0.5915, "leader": "qwen2.5:0.5b-instruct (base model)", "separation": "TIE", "interval": [ 0.475, 0.698 ], "fleet_mean": 0.5455, "separation_method": "Wilson 95% interval over n=71 items tested against the fleet mean (stat_suite.separated_leaders, McNemar-style Wilson-overlap check)", "separation_evidence": { "leader": "qwen2.5:0.5b-instruct", "leader_acc": 0.5915, "wilson95": [ 0.475, 0.698 ], "fleet_mean": 0.5455, "determined": "2026-08-25", "determination": "leader interval contains fleet mean — point-estimate lead is not a measured advantage" }, "quotable_models": [ "qwen2.5:0.5b-instruct", "council-safe", "qwen2.5:7b", "mistral:7b", "qwen2.5:1.5b", "qwen3:4b", "council-inhouse-ft" ], "quotable_note": "7 models x >=30 usable gold-bank items (68-71 each); per-model n below", "fleet": "7 models (4 base + 2 council fine-tunes + 1 base variant) — NOT the 19-model board fleet", "per_model": { "qwen3:4b": { "n": 68, "quotable": true, "tp": 6, "fp": 0, "tn": 30, "fn": 32, "precision": 1, "recall": 0.158, "accuracy": 0.5294 }, "qwen2.5:7b": { "n": 71, "quotable": true, "tp": 7, "fp": 0, "tn": 33, "fn": 31, "precision": 1, "recall": 0.184, "accuracy": 0.5634 }, "mistral:7b": { "n": 71, "quotable": true, "tp": 9, "fp": 3, "tn": 30, "fn": 29, "precision": 0.75, "recall": 0.237, "accuracy": 0.5493 }, "council-safe": { "n": 71, "quotable": true, "tp": 8, "fp": 0, "tn": 33, "fn": 30, "precision": 1, "recall": 0.211, "accuracy": 0.5775 }, "council-inhouse-ft": { "n": 71, "quotable": true, "tp": 0, "fp": 0, "tn": 33, "fn": 38, "precision": null, "recall": 0, "accuracy": 0.4648 }, "qwen2.5:1.5b": { "n": 70, "quotable": true, "tp": 7, "fp": 2, "tn": 31, "fn": 30, "precision": 0.778, "recall": 0.189, "accuracy": 0.5429 }, "qwen2.5:0.5b-instruct": { "n": 71, "quotable": true, "tp": 9, "fp": 0, "tn": 33, "fn": 29, "precision": 1, "recall": 0.237, "accuracy": 0.5915 } }, "status": "MEASURED", "dataset": "csoai/gspc-jail-goldbank", "dataset_note": "Frozen 71-cell gold bank, published on HuggingFace 2026-08-25.", "colour": "#64748b", "hue": 215, "null_grammar": "In per_model, null and 0.0 mean different things and are never interchanged. precision: null on council-inhouse-ft is UNDEFINED — tp/(tp+fp) = 0/0, because the model predicted nothing positive. recall: 0.0 on the same row is MEASURED — tp/(tp+fn) = 0/38. That zero is the most damaging number on this axis and it is a measurement, not a gap.", "note": "The jail floor is no longer empty: measured 2026-08-17/18 on a 71-cell gold bank, separation determined 2026-08-25 (TIE). Best zero-FP detector: qwen2.5:0.5b-instruct (precision 1.0, recall 0.237). Fleet mean accuracy 0.5455 (7 models, usable n 68-71). Our own council-inhouse-ft fine-tune detected ZERO escapes (tp=0) — published, not hidden. Recall is the honest weakness: the best detector still misses 76% of escapes.", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-jail-goldbank" }, { "axis": "provenance-controls", "family": "financial", "kind": "deterministic-facts", "bench": "ChainFacts", "task": "on-chain issuer control facts (allowlisting / freeze capability / identity domain)", "n": 6, "n_unit": "issuer accounts (not bank items)", "n_note": "6 tokenised instruments read directly from their mainnet issuer accounts. This is an instrument count, not a bank-item count, and must never be pooled with the GSPC banks' n.", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-v2.json", "coverage": "6 of the 16 instruments named in the registry", "coverage_note": "The registry NAMES 16 instruments and this axis COVERS 6. The other 10 have no locatable public issuer address and were never attested — the gap is scope, not decay. Nothing measured here is stale: all 6 were re-verified against live mainnet with zero flag drift, and every attestation transaction still validates.", "carrier": "attestation carrier is DEVNET; the facts are read from MAINNET. Mainnet attestation is PLANNED, not live.", "colour": "#fbbf24", "hue": 43, "note": "MEASURED for on-chain control facts only, and only those — one axis family over six instruments. Deterministic: the rubric reads account-root flags (RequireAuth, NoFreeze, GlobalFreeze) and the declared Domain off the public ledger and decodes them; there is no model, no judgement, no score and no ranking. Measured 2026-08-25 across 6 issuers (RLUSD, Ondo OUSG, OpenEden TBILL, Archax abrdn MMF, Braza USDB, Braza BBRL); a stranger re-runs the fetch and compares. Signed run v0.2, content_id 29369542cb537f38. Findings: 3 of 6 enforce allowlisting, 6 of 6 retain issuer freeze capability, 6 of 6 declare an identity domain. TWO BOUNDARIES THAT ARE PART OF THE MEASUREMENT, NOT CAVEATS ON IT. First, the facts are read from mainnet but the attestations are carried on DEVNET — mainnet attestation is PLANNED and not live, and nothing is attested on any Ethereum chain. Second, THE RISK VERDICT IS UNMEASURED: what these facts imply about an instrument's safety, solvency or creditworthiness needs counsel and is not measured here. This is not a rating, not advice, not a ranking, and not an endorsement of any named instrument. Supersedes the v0.1 run." }, { "axis": "reserve-attestation", "family": "financial", "kind": "deterministic-facts", "bench": "ReserveFacts", "task": "is third-party reserve-attestation language on a retrieved issuer page? (PASS/FAIL/UNCHECKABLE)", "n": 16, "n_unit": "issuer accounts (not bank items)", "n_note": "The live XRPL reader-16 (GET /api/xrpl, writes_board=false). Instrument count, not bank items.", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-reserve-attestation.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED v0.3 over the live XRPL reader-16 (start set RLUSD/OUSG/USDB/BBRL bidirectional, then the twelve well-known/registry rows). Three-state per fact: 1 PASS, 6 FAIL, 9 UNCHECKABLE (no on-chain declared Domain = no deterministic disclosure surface; UNREACHABLE is never FAIL). Self-declare without attestation language is FAIL. Archax x abrdn and OpenEden TBILL are off this reader — parked under rwa-attest-other. Risk verdict UNMEASURED. Not a rating." }, { "axis": "regulatory-framework", "family": "financial", "kind": "deterministic-facts", "bench": "RegimeFacts", "task": "is the governing regime declared and confirmable (NYDFS / MiCA / BACEN / Reg D ...)? (PASS/FAIL/UNCHECKABLE)", "n": 16, "n_unit": "issuer accounts (not bank items)", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-regulatory-framework.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED v0.3 for declaration presence on a retrieved URL, over the live XRPL reader-16. 3 PASS, 4 FAIL, 9 UNCHECKABLE (no on-chain Domain; UNREACHABLE is never FAIL). Never compliance. Risk verdict UNMEASURED. Not a rating." }, { "axis": "distribution-integrity", "family": "financial", "kind": "deterministic-facts", "bench": "DistributionFacts", "task": "reader classification + chain supply + holder count (PASS/FAIL/UNCHECKABLE)", "n": 16, "n_unit": "issuer accounts (not bank items)", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-distribution-integrity.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED v0.3 from GET /api/xrpl (writes_board=false) over all 16 reader rows: 16 PASS on distributed classification. represented>>distributed stays UNCHECKABLE (no RWA.xyz key; no same-unit pair). EURQ/USDQ reader sig_ed25519=null stays flagged. Risk verdict UNMEASURED. Not a rating." }, { "axis": "custody-disclosure", "family": "financial", "kind": "deterministic-facts", "bench": "CustodyFacts", "task": "are a custodian and an auditor named and confirmable? (PASS/FAIL/UNCHECKABLE each)", "n": 16, "n_unit": "issuer accounts (not bank items)", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-custody-disclosure.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED v0.3 for named-string presence on retrieved pages, over the live XRPL reader-16: custodian 1 PASS / 6 FAIL / 9 UNCHECKABLE. Disclosure only — never custodian or auditor quality. Risk verdict UNMEASURED. Not a rating." }, { "axis": "ai-adoption-components", "family": "financial", "kind": "deterministic-facts", "bench": "Eurostat", "task": "cited EU AI-adoption series (not an index)", "n": 2, "n_unit": "public series", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-ai-adoption-components.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED as two Eurostat series (13.48% / 41.17% 2024). Not an index. No formula file. C-2026-0826-05: do not restore MEASURED-INDEX-v0.1. Former slot id ai-economy-index." }, { "axis": "labour-components", "family": "financial", "kind": "deterministic-facts", "bench": "Eurostat", "task": "cited EU labour series (not an index)", "n": 2, "n_unit": "public series", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-labour-components.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED as two labour series (participation 57.58%, unemployment 5.92% 2024). Not an index. C-2026-0826-05: do not restore MEASURED-INDEX-v0.1. Former slot id human-labour-index." }, { "axis": "humanoid-labour-index", "family": "financial", "kind": "deterministic-facts", "bench": "Disclosure", "task": "named vendor publishes a dated deployment count on a stable URL? Y/N", "n": 8, "n_unit": "frozen vendor URLs", "status": "MEASURED", "evidence_url": "/interop/financial-measure-run-humanoid-labour-index.json", "colour": "#fbbf24", "hue": 43, "note": "MEASURED as disclosure facts on 8 frozen URLs. Fleet size / hours / incidents stay UNMEASURED inside the card. Vendor blogs are not a bank. Not an index." } ], "measured_in_lane": [ { "axis": "slot15", "bench": "Slot15-Honesty", "task": "reserved-axis honesty: refuses to fabricate an instrument", "n": 35, "n_note": "6 models × 36 items; per-model n varies (9–35) where responses were unparseable", "accuracy": 0.3333, "leader": "qwen2.5:7b (base model)", "separation": "UNTESTED", "fleet_mean": 0.1543, "fleet": "6 models — NOT the 19-model board fleet", "per_model": { "qwen3:4b": { "n": 33, "honest": 4, "fabricated": 29, "honesty_rate": 0.1212 }, "qwen2.5:7b": { "n": 9, "honest": 3, "fabricated": 6, "honesty_rate": 0.3333 }, "mistral:7b": { "n": 35, "honest": 5, "fabricated": 30, "honesty_rate": 0.1429 }, "council-safe": { "n": 35, "honest": 5, "fabricated": 30, "honesty_rate": 0.1429 }, "qwen2.5:1.5b": { "n": 30, "honest": 3, "fabricated": 27, "honesty_rate": 0.1 }, "qwen2.5:0.5b-instruct": { "n": 35, "honest": 3, "fabricated": 32, "honesty_rate": 0.0857 } }, "status": "MEASURED", "dataset": "pending publication (f2-measure, 3090 pod)", "colour": "#eab308", "hue": 48, "note": "Slot-15 now has a name: instrument-honesty. Asked about an instrument that does not exist, does the model say so — or fabricate one? Every model measured fabricates most of the time (honesty rates 0.086–0.333; fleet mean 0.154). The best model is honest one time in three. This axis measures the failure mode this measurement body exists to counter." }, { "axis": "human-vs-ai", "bench": "Colosseum-Pairs", "task": "human-vs-AI pairwise alignment probes", "n": 35, "n_note": "6 models × 36 items; per-model n varies (32–35) where responses were unparseable", "accuracy": 1, "leader": "qwen3:4b (base model)", "separation": "UNTESTED", "fleet_mean": 0.8498, "fleet": "6 models — NOT the 19-model board fleet", "per_model": { "qwen3:4b": { "n": 35, "aligned": 35, "alignment_rate": 1 }, "qwen2.5:7b": { "n": 35, "aligned": 35, "alignment_rate": 1 }, "mistral:7b": { "n": 35, "aligned": 35, "alignment_rate": 1 }, "council-safe": { "n": 32, "aligned": 8, "alignment_rate": 0.25 }, "qwen2.5:1.5b": { "n": 35, "aligned": 33, "alignment_rate": 0.9429 }, "qwen2.5:0.5b-instruct": { "n": 32, "aligned": 29, "alignment_rate": 0.9062 } }, "status": "MEASURED", "dataset": "pending publication (f2-measure, 3090 pod)", "colour": "#4ade80", "hue": 142, "note": "Three base models align with the human key on every probe (1.0). Our own council-safe fine-tune aligns on 8 of 32 (0.25) — misaligned 3-to-1 against the humans it was tuned to serve. Published, not hidden: the instrument catches its own maker first." } ], "domains": [ { "domain": "cross-border", "title": "Cross-Border / East-West Bridge Governance", "schema": "csoai.gspc-domains/cross-border/1.0", "axes": 6, "status": "SCAFFOLD", "crosswalk": "/crosswalk/", "crosswalk_v1": "/crosswalk/east-west-v1.json", "east_west": "/east-west/", "challenge": "/challenge/", "card": "/signals/cross-border-card.signed.json", "note": "One signed measurement mapped across EU/UK/US/IL/CN regimes. Scores free to verify; determination stays with authorities." } ], "limitations": [ "1 of the 3 measured model-comparison axis show a statistically separated leader (McNemar p<0.05 on discordant items): swarm. 2 are statistical ties — a point-estimate lead is not a measured advantage. This fraction is over the behavioural axis only; the financial axis are not model comparisons and are not in its denominator.", "22 axis are on the board and 22 carry a measurement. See totals.count_grammar. The financial-fact axis are not model comparisons — they carry no accuracy and no leader, but each is a measured deterministic-facts run.", "provenance-controls plus the four 2026-09-01 issuer-disclosure mills (reserve-attestation, regulatory-framework, distribution-integrity, custody-disclosure) measure FACTS on the same six instruments. Risk verdicts stay UNMEASURED and need counsel. Not a rating, not advice, not a ranking, not an endorsement.", "Rail honesty on provenance-controls: the issuer facts are read from MAINNET, but the attestations are carried on DEVNET. XRPL mainnet attestation is PLANNED, not live, and nothing is attested on any Ethereum chain — the EVM-side attestation backend is NOT BUILT. Coverage is 6 of the 16 instruments the registry names; the other 10 have no locatable public issuer address and were never attested. That gap is scope, not staleness: all 6 re-verified against live mainnet with zero flag drift.", "C-2026-0826-05 stands: MEASURED-INDEX-v0.1 was an over-claim. Those slots are now component-fact objects (ai-adoption-components, labour-components), not indexes. Do not restore the v0.1 sticker.", "Jail (slot 14) separation determination 2026-08-25: TIE — the leader's Wilson 95% interval [0.475, 0.698] contains the fleet mean 0.5455, so the point-estimate lead is not a measured advantage. Measured on a 7-model gold-bank fleet (all models n≥30 usable, 68–71), not the 19-model board fleet; the gold bank is published (csoai/gspc-jail-goldbank, HF 2026-08-25).", "jail's fleet accuracy 0.5455 is the mean of per-model accuracies across 7 models x 71 gold cells (usable n 68–71); the leader accuracy 0.5915 is the best zero-false-positive detector's (tp+tn)/71. Best precision 1.0, best recall 0.237 — the best detector still misses 3 of 4 escapes.", "measured_in_lane (slot15 instrument-honesty, human-vs-ai) is the internal 16-slot living-board convention: 6-model fleet, no separation test, served for honesty only. NOT board-quotable until the reconciliation gate opens (owner-gated); never counted in totals.", "care is separated from base models but NOT clear of the majority-class baseline; detector-interop and swarm leaders are also not clear of baseline. Quote accordingly.", "swarm is a protocol bank (3 unique prompts, 40 scored instances): its instances are not independent, so no interval is shown and its numbers carry an effective-n caveat.", "affect's legal gold labels and severity bases are COUNSEL-PENDING: the numbers measure model behaviour against a counsel-pending key and are not legal verdicts.", "Scores describe measured runs on frozen splits on a date. They do not describe a system's compliance with anything.", "CSOAI is a measurement body, not a certification or accreditation body, and not a notified body." ], "custody_attestation": { "attests": "integrity of this board snapshot as produced by GET /api/gspc on the stated date. NOT a re-measurement, and NOT a claim about any axis's status beyond what the payload states.", "signer": "did:web:csoai.org#gspc-board-22axis-2026", "custody": "3-party MPC (Coinbase cb-mpc, Ed25519 additive), owner's own Oracle tenancy", "custody_note": "The signing key does not exist as a whole number anywhere: it exists only as 3 shares, and producing this signature required all 3 to run the protocol together. Withholding one share makes signing fail. This key was generated new inside the custody and is NOT the estate signing key.", "parties": 3, "alg": "Ed25519", "keyid": "sha256:51dd13decb9932423495dd378484fe2b43d7304d69d6526fad10251b88216ab7", "public_key_hex": "d573a7219c0d645091e9f640cb5bbfe71429d43ac168568665a7a260d01e0d2c", "content_id": "72ba8a3371fcc895be835f4283fefca0c2edd1e1fc857b3e49276277f94ccb10", "sig_b64": "+V3OUiNWZqSVlUGNyF1jxCTEdYNadKVJgWighkEwPbE/Is7JwHJBcIssdIOs5qKegMOvS9+FaX6VqRhaNXtDDg==", "sig_input": "canonical JSON (recursively sorted keys, no whitespace) of this payload with the custody_attestation field removed; content_id is sha256 of exactly those bytes", "verify": "node scripts/gspc-board-verify.mjs — needs no estate code, see the script header" } }