{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SI3V6ELHPMRDPCRFILDNGWWW5D","short_pith_number":"pith:SI3V6ELH","canonical_record":{"source":{"id":"2407.00908","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T02:20:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a69933dd739a3d2579dd02cd891f815a40406089dbb63425dca12f328873f0c0","abstract_canon_sha256":"e277a4bd9c69f24f7b512db9e244d67e414cca6c765145d90130fdffa6ffb783"},"schema_version":"1.0"},"canonical_sha256":"92375f11677b22378a2542c6d35ad6e8dcd3e0f968e24b0c15f737beda36d91c","source":{"kind":"arxiv","id":"2407.00908","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00908","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00908v3","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00908","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"pith_short_12","alias_value":"SI3V6ELHPMRD","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"pith_short_16","alias_value":"SI3V6ELHPMRDPCRF","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"pith_short_8","alias_value":"SI3V6ELH","created_at":"2026-07-05T08:46:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SI3V6ELHPMRDPCRFILDNGWWW5D","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00908","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T02:20:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a69933dd739a3d2579dd02cd891f815a40406089dbb63425dca12f328873f0c0","abstract_canon_sha256":"e277a4bd9c69f24f7b512db9e244d67e414cca6c765145d90130fdffa6ffb783"},"schema_version":"1.0"},"canonical_sha256":"92375f11677b22378a2542c6d35ad6e8dcd3e0f968e24b0c15f737beda36d91c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:26.799774Z","signature_b64":"rWTY3ULX5WlPRO/QYoTXTeUYqxORmOlwIDYST3fvBUt/0T3MylBhdb41x+lu9nsI8JDEq4uIqQUDmKVrxWZuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92375f11677b22378a2542c6d35ad6e8dcd3e0f968e24b0c15f737beda36d91c","last_reissued_at":"2026-07-05T08:46:26.799190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:26.799190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00908","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXo8HdNWFqtd96szA57xI40sH6bfqGgyGhO/sYvEOCez9AbS7Vu7bBT6g081DEZL5vAMnE4lUXwvMy2MEfktDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:16.630691Z"},"content_sha256":"332c0e6e70b7375ce3b34200bfd2b030ff378f52c6b3bf97a9c88477005238cd","schema_version":"1.0","event_id":"sha256:332c0e6e70b7375ce3b34200bfd2b030ff378f52c6b3bf97a9c88477005238cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SI3V6ELHPMRDPCRFILDNGWWW5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Su, Hwanjun Song, Igor Shalyminov, Jason Cai, Saab Mansour","submitted_at":"2024-07-01T02:20:28Z","abstract_excerpt":"Automated evaluation is crucial for streamlining text summarization benchmarking and model development, given the costly and time-consuming nature of human evaluation. Traditional methods like ROUGE do not correlate well with human judgment, while recently proposed LLM-based metrics provide only summary-level assessment using Likert-scale scores. This limits deeper model analysis, e.g., we can only assign one hallucination score at the summary level, while at the sentence level, we can count sentences containing hallucinations. To remedy those limitations, we propose FineSurE, a fine-grained e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00908","kind":"arxiv","version":3},"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/2407.00908/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":"2026-07-05T08:46:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBoa2gZ/Rmv0RVp064fIlI2mnZ4m4Cv7eUJfEcLXga3JuOFbZ6Grtr8UnKD9taJAshcslyGAXER7ghiXQorJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:16.631448Z"},"content_sha256":"2e45853ad66cd10cb003625bc3044c4c70a7d34cba02aeaa977d0f80858722f7","schema_version":"1.0","event_id":"sha256:2e45853ad66cd10cb003625bc3044c4c70a7d34cba02aeaa977d0f80858722f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SI3V6ELHPMRDPCRFILDNGWWW5D/bundle.json","state_url":"https://pith.science/pith/SI3V6ELHPMRDPCRFILDNGWWW5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SI3V6ELHPMRDPCRFILDNGWWW5D/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":"2026-08-08T12:57:16Z","links":{"resolver":"https://pith.science/pith/SI3V6ELHPMRDPCRFILDNGWWW5D","bundle":"https://pith.science/pith/SI3V6ELHPMRDPCRFILDNGWWW5D/bundle.json","state":"https://pith.science/pith/SI3V6ELHPMRDPCRFILDNGWWW5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SI3V6ELHPMRDPCRFILDNGWWW5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SI3V6ELHPMRDPCRFILDNGWWW5D","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":"e277a4bd9c69f24f7b512db9e244d67e414cca6c765145d90130fdffa6ffb783","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T02:20:28Z","title_canon_sha256":"a69933dd739a3d2579dd02cd891f815a40406089dbb63425dca12f328873f0c0"},"schema_version":"1.0","source":{"id":"2407.00908","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00908","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00908v3","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00908","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"pith_short_12","alias_value":"SI3V6ELHPMRD","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"pith_short_16","alias_value":"SI3V6ELHPMRDPCRF","created_at":"2026-07-05T08:46:26Z"},{"alias_kind":"pith_short_8","alias_value":"SI3V6ELH","created_at":"2026-07-05T08:46:26Z"}],"graph_snapshots":[{"event_id":"sha256:2e45853ad66cd10cb003625bc3044c4c70a7d34cba02aeaa977d0f80858722f7","target":"graph","created_at":"2026-07-05T08:46:26Z","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/2407.00908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated evaluation is crucial for streamlining text summarization benchmarking and model development, given the costly and time-consuming nature of human evaluation. Traditional methods like ROUGE do not correlate well with human judgment, while recently proposed LLM-based metrics provide only summary-level assessment using Likert-scale scores. This limits deeper model analysis, e.g., we can only assign one hallucination score at the summary level, while at the sentence level, we can count sentences containing hallucinations. To remedy those limitations, we propose FineSurE, a fine-grained e","authors_text":"Hang Su, Hwanjun Song, Igor Shalyminov, Jason Cai, Saab Mansour","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T02:20:28Z","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00908","kind":"arxiv","version":3},"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":"sha256:332c0e6e70b7375ce3b34200bfd2b030ff378f52c6b3bf97a9c88477005238cd","target":"record","created_at":"2026-07-05T08:46:26Z","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":"e277a4bd9c69f24f7b512db9e244d67e414cca6c765145d90130fdffa6ffb783","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T02:20:28Z","title_canon_sha256":"a69933dd739a3d2579dd02cd891f815a40406089dbb63425dca12f328873f0c0"},"schema_version":"1.0","source":{"id":"2407.00908","kind":"arxiv","version":3}},"canonical_sha256":"92375f11677b22378a2542c6d35ad6e8dcd3e0f968e24b0c15f737beda36d91c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92375f11677b22378a2542c6d35ad6e8dcd3e0f968e24b0c15f737beda36d91c","first_computed_at":"2026-07-05T08:46:26.799190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:26.799190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWTY3ULX5WlPRO/QYoTXTeUYqxORmOlwIDYST3fvBUt/0T3MylBhdb41x+lu9nsI8JDEq4uIqQUDmKVrxWZuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:26.799774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00908","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:332c0e6e70b7375ce3b34200bfd2b030ff378f52c6b3bf97a9c88477005238cd","sha256:2e45853ad66cd10cb003625bc3044c4c70a7d34cba02aeaa977d0f80858722f7"],"state_sha256":"a646f86e799f857b11b64afc0167ccd9b979bbc199088a0b00875a7ba6af0852"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pzax4r6QS+yfqb1KPZMw2rgMjtuo/dRbHAW1MC3e6THWAZOSFm/PMcUQtEuQ0+rC+Uwycb7ylSDpvbriPKETAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:57:16.637848Z","bundle_sha256":"374c04d24a72a8553195f0a24bb5dda2278c589fb3bff5cc5b3ffd4f84b91c41"}}