{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EUSQZGQK443GPY4566JVX4FCQQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d0b3f5a7d710c305ee73e9f528392d7cb27241b4d557f8399c63ddf949a9e885","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T00:34:17Z","title_canon_sha256":"205ff5995a9d3f2efa5750b6e8eaea94a1bbfeddda2cc5730f9d3d026dd38dc9"},"schema_version":"1.0","source":{"id":"2605.24305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24305","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24305v1","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24305","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"EUSQZGQK443G","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"EUSQZGQK443GPY45","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"EUSQZGQK","created_at":"2026-05-26T01:02:58Z"}],"graph_snapshots":[{"event_id":"sha256:5e205bb61241c5f1890702f84fea4066fac7f50a9392e87266e25da2f773bca2","target":"graph","created_at":"2026-05-26T01:02:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.24305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason about parameter-dependent dynamics. We present ChaosBench-Logic v2, a 40,886-question benchmark over 165 dynamical systems with 27 FOL predicates and 78 axiom edges, together with CARE (Calibration- and Adversarial-Robust Evaluation), a protocol that surfaces these pathologies. Evaluating 14 models, we find that regime-transition reasoning remains near random (MCC = 0.05) even for frontier models, whereas FOL deduction with given premises reache","authors_text":"Noel Thomas","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T00:34:17Z","title":"ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24305","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:da81065cea319370a0d6a8df8985485c16cf5a8e4bba12d4bddfd9da13751cb1","target":"record","created_at":"2026-05-26T01:02:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d0b3f5a7d710c305ee73e9f528392d7cb27241b4d557f8399c63ddf949a9e885","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T00:34:17Z","title_canon_sha256":"205ff5995a9d3f2efa5750b6e8eaea94a1bbfeddda2cc5730f9d3d026dd38dc9"},"schema_version":"1.0","source":{"id":"2605.24305","kind":"arxiv","version":1}},"canonical_sha256":"25250c9a0ae73667e39df7935bf0a28410500a956606e5dc78c4ee3a5d5f928c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25250c9a0ae73667e39df7935bf0a28410500a956606e5dc78c4ee3a5d5f928c","first_computed_at":"2026-05-26T01:02:58.815763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:58.815763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ux3JlezjoR51yzL1CsX1pEs+RqQbBA+azpSOr7jO9Vbm/OC0PX73kFlYsjAYjv068FMKyLA7eQR0uToIAazpDw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:58.816533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da81065cea319370a0d6a8df8985485c16cf5a8e4bba12d4bddfd9da13751cb1","sha256:5e205bb61241c5f1890702f84fea4066fac7f50a9392e87266e25da2f773bca2"],"state_sha256":"072cca0d1e0a728e71a7985950fde676cb1c2e0be96b73cebd16f172b23b8a23"}