{ "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": "4485aa3ba81947b9766e014bdbab08b857dd989287bf1fd3a2df9d5607cd249de3e74e0fe58c06f7b79a6e4b866bff674b6245eef40cadc2080b532b6a568b0d", "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": 0.5865, "separation": "TIE" }, { "axis": "safety", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 36, "accuracy": 0.9444, "separation": "TIE" }, { "axis": "provenance", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 32, "accuracy": 0.7188, "separation": "TIE" }, { "axis": "continuity", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 33, "accuracy": 0.6061, "separation": "TIE" }, { "axis": "conformance", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 35, "accuracy": 0.7143, "separation": "TIE" }, { "axis": "openness", "family": "gspc", "kind": "model-comparison", "status": "MEASURED", "n": 32, "accuracy": 0.8438, "separation": "TIE" }, { "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": 0.405, "separation": "TIE" }, { "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": 0.4444, "separation": "UNTESTED" }, { "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": "effect-binding", "family": "gspc", "kind": "deterministic-facts", "status": "MEASURED", "n": 261, "accuracy": null, "separation": null }, { "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 signed card index (/signed/card_index.json, corpus 3 in council-os/CARD-CORPORA.md; whole-store check at /api/state → card_chain.bodies_verified_valid) under #card-attestation-1, and site_attestation on this payload under #board-attestation-1; check those instead. The older 150-card figure was a checked subset of that same chain, not a separate corpus.", "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" }, "peritem_sha256": "0d8dacfbe7384a5d2f6a83e7455482ab75f935366bbb6e18da61cfdac8890dec" }, "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" ], "run_attestation": [ "ED25519_SIGNED", "CONTENT_ADDRESSED_UNSIGNED" ], "public_leader_state_absent": "the leader is shown (a public score)", "leader_card_state": [ "SIGNED_PER_MODEL_CARD", "NO_SIGNED_PER_MODEL_CARD", "CARD_RECORDS_A_DIFFERENT_MEASUREMENT" ], "separation_untested_reason_code": [ "NO_SIGNED_CARD_FOR_AXIS", "ROWS_ARE_A_RETIRED_BANK", "TOO_FEW_DISTINCT_ITEMS" ], "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": 1, "measured_axes": 1, "unmeasured_axes": 0, "quotable_axes": 1, "public_count": "1 axis · 1 measured", "separation_public_count": "0 of 0 model-comparison axes separated a leader · 0 TIE · 0 UNTESTED", "separation_public_count_note": "Read with public_count, never instead of it. measured_axes counts axis with a RUN behind them; it is not a count of axis with a separated leader. SEPARATED, TIE and UNTESTED are three states and none is folded into another. Derived from the axis array, never typed. The same three numbers appear below as separated_leads / ties / untested_separations and in limitations[0]; there is one derivation.", "model_fleets": 0, "fact_runs": 1, "count_grammar": "1 axis is 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. A measurement is not a separated leader: 0 of 0 model-comparison axes separated a leader · 0 TIE · 0 UNTESTED. A point-estimate lead is not a measured advantage, and UNTESTED is not a tie.", "by_family": { "gspc": { "axes": 0, "measured": 0, "note": "The 14 behavioural axes: a model fleet answers a frozen bank, graded deterministically. Plus effect-binding (ADR-002), a deterministic-facts probe of tool-call SERVERS, not a fleet: n counts servers probed, it has no leader, no accuracy and no separation, and it joins no mean." }, "financial": { "axes": 1, "measured": 1, "as_of": "2026-09-07T11:30:35Z", "reader_state": "REACHABLE", "reader_as_of": "2026-09-06T23:49:21Z", "source": "/interop/financial-facts-as-of.json", "risk_verdict": "UNMEASURED", "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). as_of is the producer run (scripts/grade_financial_ledgers.py), never a typed 2026-08-25." } }, "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 published deterministic-facts run artifacts. Today 1 of 1 axis on the board carry a run behind them: 0 model-comparison and 1 deterministic-fact axes. The fact axes carry no accuracy and no leader — measured is not the same as scored. 0 run artifacts carry an Ed25519 signature; 1 is content-addressed but unsigned. No signature is inferred from a content_id.", "financial_run_attestations": { "run_artifacts": 1, "ed25519_signed": 0, "content_addressed_unsigned": 1, "signed_axes": [], "unsigned_axes": [ "distribution-integrity" ], "note": "Derived from each deterministic-facts axis's run_attestation field, in BOTH families since 2026-09-22 (effect-binding is a gspc-family fact run). A content_id proves identity of bytes, not signer authorization." }, "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": 16, "items_note": "items sums each axis's n. Financial-axis n values count issuer accounts, public series, or frozen vendor URLs as declared on each row — not bank items. Unmeasured slots contribute 0 because nothing was measured. Read items as 'rows behind the board', not as a single comparable sample.", "comparison_axes": 0, "separated_leads": 0, "ties": 0, "untested_separations": 0, "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": 0, "public_leader_count": 0, "lid": "1 axes measured · 0 model fleets · 0 separated leaders · 0 public leader scores · 1 fact runs · TIE is TIE · not a certificate.", "own_leaders_excluded": 0, "own_leaders_excluded_axes": [], "own_model_exclusion_note": "Own council-specialist models were removed from the public per-axis leaders on 0 of the 0 model-comparison axes (none); 0 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": 0, "uncarded_leaders_dropped_axes": [], "uncarded_leader_note": "The public per-axis leader was removed on 0 of the 0 model-comparison axes (none) 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": null, "mean_accuracy": null, "mean_fleet_mean": null, "mean_harm": null, "mean_unparsed_rate": null, "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." }, "peritem_rows": { "dataset": "csoai/gspc-peritem-rows-2026-08-12", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-peritem-rows-2026-08-12", "dataset_revision": "294e4cf9e8b72a00aa50de024b3ed3e7ab0b3361", "licence": "CC-BY-4.0", "peritem_sha256": "0d8dacfbe7384a5d2f6a83e7455482ab75f935366bbb6e18da61cfdac8890dec", "peritem_sha256_is": "sha256 of the dataset's SHA256SUMS file bytes — one line ' rows/' per row file, sorted by file name. Recompute: sha256sum rows/*.jsonl > SHA256SUMS; sha256sum SHA256SUMS.", "rows_total": 15580, "files": { "peritem_affect.jsonl": "7e8a612889d486df40ba638e36ba976cd2820460272fe65c0202e271c95e99e7", "peritem_agi.jsonl": "b70ccaa015668a80aeb50196623e8a138b6238e023b6cdff4308ee4fd592b2cb", "peritem_art5.jsonl": "950861961ed3e1d0481c4577850b908b41ef696785b500956f11c502015cf1a3", "peritem_asi.jsonl": "f90910c6cede5f97a1158226535020c17cf6f7f22a19ce65201511b179ef9e40", "peritem_care.jsonl": "888f230b58e5d78a8570244b9e8374c9740f24c3d6fd9f45d67b372db25f27b2", "peritem_det.jsonl": "665e358bedbaf899620fd5119a2a9d9b1415eb91396a463955c0e667c21b94a3", "peritem_gov.jsonl": "3a1d3193d3651448dd311efe4c7efcbdffb19e07fba06c15e628b844bfbfa2a5", "peritem_mach.jsonl": "d3133100c2889cf259f2faa5390c69ccd3c71ac157fbb4ccd369b3c679996a0b", "peritem_mcp.jsonl": "9ac4db30d9d0039555702445ab940346974da36b4b1d8de58dc775849caa26da", "peritem_oss.jsonl": "f04421a8a8b4a6f01d79dfe771ede8ef40de4338955dcb64a48244df9008685f", "peritem_prv.jsonl": "fb9efe3afda9d075cf38607c53f1c6a8044909b642e58747b9559a87fcc83237", "peritem_swarm.jsonl": "0a54c4abae07d638d25e7121771500dfc3f40ad0a40a46279a1b6a4dc17f6212", "peritem_xr.jsonl": "34758dd55d2b632e8a2a26390c3f1e01d7044a92e8c38d7ee76bd0386bcc8a6a" }, "record": "/interop/gspc-peritem-rows-2026-08-12.json", "signed_record": "/interop/gspc-peritem-rows-2026-08-12.signed.json", "producer": "scripts/gspc_separation_from_rows.py", "rule": "Leader vs best base model; SEPARATED iff exact McNemar p<0.05 on discordant items, else TIE (decided 2026-08-13). Wilson 95% intervals are annotation only.", "own_model_exclusion": "CSOAI's own fine-tunes (sov6-*-v3-light in the rows; council-*-v3-light on the board) are removed before ranking. Base fleet of 6.", "publication_rule": "A determination is published only on an axis that carries signed cards in /signed/card_index.json and whose rows are the bank the board row serves. Elsewhere the axis stays UNTESTED with its reason.", "frozen_manifests_note": "The signed 2026-08-13 board-freeze manifests carry peritem_sha256: null (the rows were not published then). They stay as signed; this record binds the rows by hash instead of editing them.", "decided_axes": [], "untested_axes": [], "leaders_without_a_signed_card_for_this_run": [], "leader_card_note": "leader shown from per-item rows; no signed per-model card yet — on every axis listed in leaders_without_a_signed_card_for_this_run. The rows back the number; no signed per-model card of this run does, and none is fabricated.", "objections": "https://councilof.ai/census/" }, "bank_host": "https://huggingface.co/datasets/", "banked_axes": 1, "banked_axes_resolvable": 1, "banked_axes_unresolvable": [], "bank_note": "1 of the 1 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": "distribution-integrity", "family": "financial", "kind": "deterministic-facts", "dataset": "csoai/gspc-distribution-integrity", "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", "run_attestation": "CONTENT_ADDRESSED_UNSIGNED", "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.", "facts_as_of": "2026-09-07T11:30:35Z", "facts_status": "MEASURED", "dataset_url": "https://huggingface.co/datasets/csoai/gspc-distribution-integrity" } ], "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": [ "Of the 0 model-comparison axes, 0 have a published statistical-separation determination: 0 SEPARATED and 0 TIE. Methods are stated per axis; most use paired McNemar tests, while any alternative must publish its basis and supporting evidence. The remaining 0 are UNTESTED for separation. All 0 carry a measurement — separation is a further test that most have not had, and UNTESTED is not a tie. A point-estimate lead is not a measured advantage. The financial axes are not model comparisons and are not in this denominator.", "1 axis is on the board and 1 carries a measurement. See totals.count_grammar. The financial-fact axes 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.", "detector-interop and the swarm point leader are not clear of baseline. Quote accordingly.", "Separation on 0 axes (none) is computed from the published per-item rows (csoai/gspc-peritem-rows-2026-08-12, peritem_sha256 0d8dacfbe7384a5d…) with the rule fixed 2026-08-13, our own models removed before ranking: 0 TIE and 0 SEPARATED. The leader on those axes is read from the rows; on 0 of them (none) no signed per-model card of this run backs it — leader shown from per-item rows; no signed per-model card yet. 0 further axes (none) have published rows but stay UNTESTED; each states its reason in separation_untested_reason.", "swarm now serves the wave-2b bank (37 independent items, 5-model fleet; n≥36 usable per cell), not the retired 3-prompt PROTOCOL bank. Its signed candidate cards support qwen2.5:7b as the point leader but do not publish paired rows or compatible intervals, so separation is UNTESTED. The old PROTOCOL result remains historical evidence and is not the active board row.", "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." ], "site_attestation": { "attests": "integrity of this board snapshot as published by the site (NOT a re-measurement)", "signer": "did:web:csoai.org#board-attestation-1", "alg": "Ed25519", "sig": "19e76108335bff6bdef69ffcc0b28e8fc312b7dddc76be13dd1003c57085403040754576d33c7fd9c9db8edd0aa0ee0578cb6fd0aed6c5b739e8e2631d45d502", "public_key_x": "k2fPWb6ctyu8l5at8FYgHsHFit_qoT-DssW3VNbCAXA", "sig_input": "Ed25519 over the RAW UTF-8 BYTES (not a digest) of canonical JSON of this payload with the site_attestation field removed. Canonical JSON here means: object keys sorted by code point, recursively; no whitespace (separators ',' and ':'); non-ASCII emitted LITERALLY as UTF-8, never as \\uXXXX escapes (Python ensure_ascii=FALSE — ensure_ascii=True is the wrong reading and will fail, this payload contains non-ASCII characters); numbers serialised by ECMAScript Number::toString, so an integral float renders 0, not 0.0. This is NOT the rule used by the signed measurement cards under /signed/cards/, which were minted with ensure_ascii=TRUE and whose ids are SHA-256 over those bytes — see /signed/HOW-TO-VERIFY.md. The two are deliberately different and are each signed over the bytes they were signed over.", "sig_input_ensure_ascii": false, "sig_input_is_digest": false, "verify": "fetch /.well-known/did.json → #board-attestation-1 public key → verify sig over the raw UTF-8 bytes of canonical(payload minus site_attestation), with ensure_ascii=False as specified in sig_input" } }