{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H7KJ23DBIAGJQOTOLUCNCKBKCT","short_pith_number":"pith:H7KJ23DB","canonical_record":{"source":{"id":"2501.00257","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T03:56:17Z","cross_cats_sorted":[],"title_canon_sha256":"e1348bd85164814880023ef41390f1eed32b2fe7ddb523759eceb6de66d65b5c","abstract_canon_sha256":"7d35bca69dd34f3f7aa2be954822225c6f3a93d4709b254b8dbd392861fd9120"},"schema_version":"1.0"},"canonical_sha256":"3fd49d6c61400c983a6e5d04d1282a14e6a5834cdf826223e063d8849281e223","source":{"kind":"arxiv","id":"2501.00257","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00257","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00257v1","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00257","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"H7KJ23DBIAGJ","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"H7KJ23DBIAGJQOTO","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"H7KJ23DB","created_at":"2026-07-05T09:55:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H7KJ23DBIAGJQOTOLUCNCKBKCT","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00257","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T03:56:17Z","cross_cats_sorted":[],"title_canon_sha256":"e1348bd85164814880023ef41390f1eed32b2fe7ddb523759eceb6de66d65b5c","abstract_canon_sha256":"7d35bca69dd34f3f7aa2be954822225c6f3a93d4709b254b8dbd392861fd9120"},"schema_version":"1.0"},"canonical_sha256":"3fd49d6c61400c983a6e5d04d1282a14e6a5834cdf826223e063d8849281e223","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:41.776435Z","signature_b64":"Sj8WPPbxDVWohm9iyNYuTjbm8gg4LKIfzppJRE1orDbi9RUbRSrOTccLqtx0yJjxRezF38A2EFjRwrfSAbHnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd49d6c61400c983a6e5d04d1282a14e6a5834cdf826223e063d8849281e223","last_reissued_at":"2026-07-05T09:55:41.775935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:41.775935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00257","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qUasHyqedY6Spygov1oOQAaM3hTyj68b3nWKKM37d+au/hwPVB6Okj8ig6oQ61jEga3CTnM6pGGzZKYKE8rCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:28.696557Z"},"content_sha256":"434b1bdc122c59926af5c0d14aa4335e5fb972142bef6f613765dee8800f72a0","schema_version":"1.0","event_id":"sha256:434b1bdc122c59926af5c0d14aa4335e5fb972142bef6f613765dee8800f72a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H7KJ23DBIAGJQOTOLUCNCKBKCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-beta","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rahul Murugan, Raymond Bernard, Shaina Raza (PhD), Subhabrata Das (PhD)","submitted_at":"2024-12-31T03:56:17Z","abstract_excerpt":"Despite the remarkable coherence of Large Language Models (LLMs), existing evaluation methods often suffer from fluency bias and rely heavily on multiple-choice formats, making it difficult to assess factual accuracy and complex reasoning effectively. LLMs thus frequently generate factually inaccurate responses, especially in complex reasoning tasks, highlighting two prominent challenges: (1) the inadequacy of existing methods to evaluate reasoning and factual accuracy effectively, and (2) the reliance on human evaluators for nuanced judgment, as illustrated by Williams and Huckle (2024)[1], w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00257","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.00257/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wezVKo7/1+Rk3oukqjxrpBysPc+C8fAqXn4yPUYPhXCLIvgl+jn8tPJYWHeeS/JDaURdEvQGdeJL/LwZySXsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:28.697177Z"},"content_sha256":"09e29fb14cb4d539d2e6ed84b0aae4bf234b0b4ba7b039955a09b73c51478a23","schema_version":"1.0","event_id":"sha256:09e29fb14cb4d539d2e6ed84b0aae4bf234b0b4ba7b039955a09b73c51478a23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT/bundle.json","state_url":"https://pith.science/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T19:47:28Z","links":{"resolver":"https://pith.science/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT","bundle":"https://pith.science/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT/bundle.json","state":"https://pith.science/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H7KJ23DBIAGJQOTOLUCNCKBKCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H7KJ23DBIAGJQOTOLUCNCKBKCT","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":"7d35bca69dd34f3f7aa2be954822225c6f3a93d4709b254b8dbd392861fd9120","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T03:56:17Z","title_canon_sha256":"e1348bd85164814880023ef41390f1eed32b2fe7ddb523759eceb6de66d65b5c"},"schema_version":"1.0","source":{"id":"2501.00257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00257","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00257v1","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00257","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"H7KJ23DBIAGJ","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"H7KJ23DBIAGJQOTO","created_at":"2026-07-05T09:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"H7KJ23DB","created_at":"2026-07-05T09:55:41Z"}],"graph_snapshots":[{"event_id":"sha256:09e29fb14cb4d539d2e6ed84b0aae4bf234b0b4ba7b039955a09b73c51478a23","target":"graph","created_at":"2026-07-05T09:55:41Z","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/2501.00257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable coherence of Large Language Models (LLMs), existing evaluation methods often suffer from fluency bias and rely heavily on multiple-choice formats, making it difficult to assess factual accuracy and complex reasoning effectively. LLMs thus frequently generate factually inaccurate responses, especially in complex reasoning tasks, highlighting two prominent challenges: (1) the inadequacy of existing methods to evaluate reasoning and factual accuracy effectively, and (2) the reliance on human evaluators for nuanced judgment, as illustrated by Williams and Huckle (2024)[1], w","authors_text":"Rahul Murugan, Raymond Bernard, Shaina Raza (PhD), Subhabrata Das (PhD)","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T03:56:17Z","title":"EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-beta"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00257","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":"sha256:434b1bdc122c59926af5c0d14aa4335e5fb972142bef6f613765dee8800f72a0","target":"record","created_at":"2026-07-05T09:55:41Z","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":"7d35bca69dd34f3f7aa2be954822225c6f3a93d4709b254b8dbd392861fd9120","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T03:56:17Z","title_canon_sha256":"e1348bd85164814880023ef41390f1eed32b2fe7ddb523759eceb6de66d65b5c"},"schema_version":"1.0","source":{"id":"2501.00257","kind":"arxiv","version":1}},"canonical_sha256":"3fd49d6c61400c983a6e5d04d1282a14e6a5834cdf826223e063d8849281e223","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fd49d6c61400c983a6e5d04d1282a14e6a5834cdf826223e063d8849281e223","first_computed_at":"2026-07-05T09:55:41.775935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:41.775935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sj8WPPbxDVWohm9iyNYuTjbm8gg4LKIfzppJRE1orDbi9RUbRSrOTccLqtx0yJjxRezF38A2EFjRwrfSAbHnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:41.776435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:434b1bdc122c59926af5c0d14aa4335e5fb972142bef6f613765dee8800f72a0","sha256:09e29fb14cb4d539d2e6ed84b0aae4bf234b0b4ba7b039955a09b73c51478a23"],"state_sha256":"a5e096a4fe7d5428c769a2ce61fb077a016e46dc2ba229734911e7e6e2c114b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SaLoyi84WYS3N6TRg4T6Vct1o2XmfZnKO8lWnFPW5ZwI2Cu3gEo4GQbDhdpJcvAUJmdiUeG1jM9+R6EhLr/vDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:47:28.702147Z","bundle_sha256":"249542ba54897a0b4ae2381a2c7a7c1201554f4211bf23dda2bab53ebb56fcef"}}