{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M427FVJB4IH6EVWPDD3WN2Z63K","short_pith_number":"pith:M427FVJB","schema_version":"1.0","canonical_sha256":"6735f2d521e20fe256cf18f766eb3edaa28ff59cb3759a1c23fdb9f38cc473a2","source":{"kind":"arxiv","id":"2506.07479","version":2},"attestation_state":"computed","paper":{"title":"Improving Fairness of Large Language Models in Multi-document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyuan Li, Rui Zhang, Snigdha Chaturvedi","submitted_at":"2025-06-09T06:52:59Z","abstract_excerpt":"Fairness in multi-document summarization (MDS) is crucial for providing comprehensive views across documents with diverse social attribute values, which can significantly impact decision-making. For example, a summarization system that tends to overrepresent negative reviews of products can mislead customers into disregarding good products. Previous works measure fairness in MDS at two levels: summary-level and corpus-level. While summary-level fairness focuses on individual summaries, corpus-level fairness focuses on a corpus of summaries. Recent methods primarily focus on summary-level fairn"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07479","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:52:59Z","cross_cats_sorted":[],"title_canon_sha256":"7f5b63bd46ca8b5d022f5c9e230130996d406c1f6893196143802cb1c2b44766","abstract_canon_sha256":"a25e7fdb2e2971fe5bbb4547694a49c7ced892c58df820c23bf0942a20c583b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:13.807727Z","signature_b64":"kYtMb4N+TYUnJzU9Bh2dfcm2qsW0Jap3oQK99+xGQiD9qtbWTx4CXCiK2SBhifdGQAK4tLzVj+eA8JeMd9r/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6735f2d521e20fe256cf18f766eb3edaa28ff59cb3759a1c23fdb9f38cc473a2","last_reissued_at":"2026-07-05T11:20:13.807227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:13.807227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Fairness of Large Language Models in Multi-document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyuan Li, Rui Zhang, Snigdha Chaturvedi","submitted_at":"2025-06-09T06:52:59Z","abstract_excerpt":"Fairness in multi-document summarization (MDS) is crucial for providing comprehensive views across documents with diverse social attribute values, which can significantly impact decision-making. For example, a summarization system that tends to overrepresent negative reviews of products can mislead customers into disregarding good products. Previous works measure fairness in MDS at two levels: summary-level and corpus-level. While summary-level fairness focuses on individual summaries, corpus-level fairness focuses on a corpus of summaries. Recent methods primarily focus on summary-level fairn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07479","kind":"arxiv","version":2},"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/2506.07479/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07479","created_at":"2026-07-05T11:20:13.807283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07479v2","created_at":"2026-07-05T11:20:13.807283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07479","created_at":"2026-07-05T11:20:13.807283+00:00"},{"alias_kind":"pith_short_12","alias_value":"M427FVJB4IH6","created_at":"2026-07-05T11:20:13.807283+00:00"},{"alias_kind":"pith_short_16","alias_value":"M427FVJB4IH6EVWP","created_at":"2026-07-05T11:20:13.807283+00:00"},{"alias_kind":"pith_short_8","alias_value":"M427FVJB","created_at":"2026-07-05T11:20:13.807283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K","json":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K.json","graph_json":"https://pith.science/api/pith-number/M427FVJB4IH6EVWPDD3WN2Z63K/graph.json","events_json":"https://pith.science/api/pith-number/M427FVJB4IH6EVWPDD3WN2Z63K/events.json","paper":"https://pith.science/paper/M427FVJB"},"agent_actions":{"view_html":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K","download_json":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K.json","view_paper":"https://pith.science/paper/M427FVJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07479&json=true","fetch_graph":"https://pith.science/api/pith-number/M427FVJB4IH6EVWPDD3WN2Z63K/graph.json","fetch_events":"https://pith.science/api/pith-number/M427FVJB4IH6EVWPDD3WN2Z63K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K/action/storage_attestation","attest_author":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K/action/author_attestation","sign_citation":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K/action/citation_signature","submit_replication":"https://pith.science/pith/M427FVJB4IH6EVWPDD3WN2Z63K/action/replication_record"}},"created_at":"2026-07-05T11:20:13.807283+00:00","updated_at":"2026-07-05T11:20:13.807283+00:00"}