{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2NMHRPB2PET67EA74VIZ44V3DH","short_pith_number":"pith:2NMHRPB2","canonical_record":{"source":{"id":"2401.02132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T08:34:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44d51cd55cc1e6b17c98874a90a83d0d7c6fbccbbf80fed26a3d9b5f70b9ef3e","abstract_canon_sha256":"3d551e5a46d95926df00c8a232ac320c75f1d65d5d63f96e174d2d279b27f4af"},"schema_version":"1.0"},"canonical_sha256":"d35878bc3a7927ef901fe5519e72bb19c71f4732c11e111d95130bcdacb68608","source":{"kind":"arxiv","id":"2401.02132","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02132","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02132v1","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02132","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"2NMHRPB2PET6","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"2NMHRPB2PET67EA7","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"2NMHRPB2","created_at":"2026-07-05T07:30:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2NMHRPB2PET67EA74VIZ44V3DH","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T08:34:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44d51cd55cc1e6b17c98874a90a83d0d7c6fbccbbf80fed26a3d9b5f70b9ef3e","abstract_canon_sha256":"3d551e5a46d95926df00c8a232ac320c75f1d65d5d63f96e174d2d279b27f4af"},"schema_version":"1.0"},"canonical_sha256":"d35878bc3a7927ef901fe5519e72bb19c71f4732c11e111d95130bcdacb68608","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:11.754247Z","signature_b64":"yJfJ4n9lbGaH0plMXo4Bvok3aH8DF7bvI/KBglZH2S/sHvifRibnm0T4aCrWsVeHpEXiH726pywq5QLFmWZ4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d35878bc3a7927ef901fe5519e72bb19c71f4732c11e111d95130bcdacb68608","last_reissued_at":"2026-07-05T07:30:11.753737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:11.753737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02132","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":"2026-07-05T07:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCqWQML+U/9nIcUJXhQeYwdOJMosq+y6ulbxF+VZlXdc/V9oL2rdWoWm/uhs7+k/w3PamMKHW5EW4oC9hf0PBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:16:02.410102Z"},"content_sha256":"28820dad51de301aa92f6e679d0468ee32383344568bdd86ec7121e08971ff7e","schema_version":"1.0","event_id":"sha256:28820dad51de301aa92f6e679d0468ee32383344568bdd86ec7121e08971ff7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2NMHRPB2PET67EA74VIZ44V3DH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bradley Malin, Jiaxin Zhang, Kamalika Das, Lopez Damien, Sricharan Kumar, Wendi Cui, Zhuohang Li","submitted_at":"2024-01-04T08:34:16Z","abstract_excerpt":"Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity, often fail to capture the holistic semantic equivalence. This results in a low correlation with human judgments and intuition, which is especially problematic in high-stakes applications like healthcare and finance where reliability, safety, and robust decision-making are highly critical. This work proposes DCR, an automated framework for evaluating and improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02132","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/2401.02132/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":"2026-07-05T07:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mNtI3b9+kGYn/oWsTi+0US7BBxKX9/qfqW0H0SkQtuQYOlLydT7fUP8oPKatVl+Q4mhAzGsPQA8h2ANh8jfBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:16:02.410996Z"},"content_sha256":"11a6e4a09e55188725f268ba3f2d6e7ddc19e0e49f1b1d853ea73a2e27797e95","schema_version":"1.0","event_id":"sha256:11a6e4a09e55188725f268ba3f2d6e7ddc19e0e49f1b1d853ea73a2e27797e95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NMHRPB2PET67EA74VIZ44V3DH/bundle.json","state_url":"https://pith.science/pith/2NMHRPB2PET67EA74VIZ44V3DH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NMHRPB2PET67EA74VIZ44V3DH/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":"2026-08-11T03:16:02Z","links":{"resolver":"https://pith.science/pith/2NMHRPB2PET67EA74VIZ44V3DH","bundle":"https://pith.science/pith/2NMHRPB2PET67EA74VIZ44V3DH/bundle.json","state":"https://pith.science/pith/2NMHRPB2PET67EA74VIZ44V3DH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NMHRPB2PET67EA74VIZ44V3DH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2NMHRPB2PET67EA74VIZ44V3DH","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":"3d551e5a46d95926df00c8a232ac320c75f1d65d5d63f96e174d2d279b27f4af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T08:34:16Z","title_canon_sha256":"44d51cd55cc1e6b17c98874a90a83d0d7c6fbccbbf80fed26a3d9b5f70b9ef3e"},"schema_version":"1.0","source":{"id":"2401.02132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02132","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02132v1","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02132","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"2NMHRPB2PET6","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"2NMHRPB2PET67EA7","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"2NMHRPB2","created_at":"2026-07-05T07:30:11Z"}],"graph_snapshots":[{"event_id":"sha256:11a6e4a09e55188725f268ba3f2d6e7ddc19e0e49f1b1d853ea73a2e27797e95","target":"graph","created_at":"2026-07-05T07:30:11Z","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/2401.02132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity, often fail to capture the holistic semantic equivalence. This results in a low correlation with human judgments and intuition, which is especially problematic in high-stakes applications like healthcare and finance where reliability, safety, and robust decision-making are highly critical. This work proposes DCR, an automated framework for evaluating and improv","authors_text":"Bradley Malin, Jiaxin Zhang, Kamalika Das, Lopez Damien, Sricharan Kumar, Wendi Cui, Zhuohang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T08:34:16Z","title":"DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02132","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":"sha256:28820dad51de301aa92f6e679d0468ee32383344568bdd86ec7121e08971ff7e","target":"record","created_at":"2026-07-05T07:30:11Z","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":"3d551e5a46d95926df00c8a232ac320c75f1d65d5d63f96e174d2d279b27f4af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T08:34:16Z","title_canon_sha256":"44d51cd55cc1e6b17c98874a90a83d0d7c6fbccbbf80fed26a3d9b5f70b9ef3e"},"schema_version":"1.0","source":{"id":"2401.02132","kind":"arxiv","version":1}},"canonical_sha256":"d35878bc3a7927ef901fe5519e72bb19c71f4732c11e111d95130bcdacb68608","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d35878bc3a7927ef901fe5519e72bb19c71f4732c11e111d95130bcdacb68608","first_computed_at":"2026-07-05T07:30:11.753737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:11.753737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yJfJ4n9lbGaH0plMXo4Bvok3aH8DF7bvI/KBglZH2S/sHvifRibnm0T4aCrWsVeHpEXiH726pywq5QLFmWZ4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:11.754247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28820dad51de301aa92f6e679d0468ee32383344568bdd86ec7121e08971ff7e","sha256:11a6e4a09e55188725f268ba3f2d6e7ddc19e0e49f1b1d853ea73a2e27797e95"],"state_sha256":"072f8c95c2a0049a6264e1be926a70e880430f82c6457469307bf64dd3e75f5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qV7tLmR8FtOB3RA722GQ7m0U2HfIMKXHfDHQk/gc2PUsRctjch45jS4aFFrPJ03pe4X3xLrAbg+4WBjYMvzHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:16:02.426444Z","bundle_sha256":"0df528ce6b700ea956189392ac4dc95107948badaf1928cc116af8a581ca55ef"}}