{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3NTZPKRQZ6KI3AA3HBHLEYESR","short_pith_number":"pith:H3NTZPKR","schema_version":"1.0","canonical_sha256":"3edb3cbd51867ca46c00d9c2759304944a7c9ff119c5ea6873a1f803820cca8a","source":{"kind":"arxiv","id":"2502.00448","version":1},"attestation_state":"computed","paper":{"title":"HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reordering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Yu, Hao Chen, Taiji Li, Yin Zhang","submitted_at":"2025-02-01T14:55:06Z","abstract_excerpt":"Despite the rapid growth of context length of large language models (LLMs) , LLMs still perform poorly in long document summarization. An important reason for this is that relevant information about an event is scattered throughout long documents, and the messy narrative order impairs the accurate understanding and utilization of LLMs for long documents. To address these issues, we propose a novel summary generation framework, called HERA. Specifically, we first segment a long document by its semantic structure and retrieve text segments about the same event, and finally reorder them to form t"},"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":"2502.00448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T14:55:06Z","cross_cats_sorted":[],"title_canon_sha256":"eefaee7168c882c8b9c0f8cfabdc409389ec81f767d310143ed46d215b62c6a5","abstract_canon_sha256":"535b17ee49eb026b7eff21cfe75179f6960918b5f77c1c6310025e06949c40d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:33.827263Z","signature_b64":"6LQG5QwFCfy5J7kpUZf2QKlhlF9jIHMLOx+4dUDsJ3GP76UL42Xcvps290wxUZ19ibtS8vjYO/cuVd7N9qrMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3edb3cbd51867ca46c00d9c2759304944a7c9ff119c5ea6873a1f803820cca8a","last_reissued_at":"2026-07-05T10:08:33.826869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:33.826869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reordering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Yu, Hao Chen, Taiji Li, Yin Zhang","submitted_at":"2025-02-01T14:55:06Z","abstract_excerpt":"Despite the rapid growth of context length of large language models (LLMs) , LLMs still perform poorly in long document summarization. An important reason for this is that relevant information about an event is scattered throughout long documents, and the messy narrative order impairs the accurate understanding and utilization of LLMs for long documents. To address these issues, we propose a novel summary generation framework, called HERA. Specifically, we first segment a long document by its semantic structure and retrieve text segments about the same event, and finally reorder them to form t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00448","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/2502.00448/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":"2502.00448","created_at":"2026-07-05T10:08:33.826927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00448v1","created_at":"2026-07-05T10:08:33.826927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00448","created_at":"2026-07-05T10:08:33.826927+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3NTZPKRQZ6K","created_at":"2026-07-05T10:08:33.826927+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3NTZPKRQZ6KI3AA","created_at":"2026-07-05T10:08:33.826927+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3NTZPKR","created_at":"2026-07-05T10:08:33.826927+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/H3NTZPKRQZ6KI3AA3HBHLEYESR","json":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR.json","graph_json":"https://pith.science/api/pith-number/H3NTZPKRQZ6KI3AA3HBHLEYESR/graph.json","events_json":"https://pith.science/api/pith-number/H3NTZPKRQZ6KI3AA3HBHLEYESR/events.json","paper":"https://pith.science/paper/H3NTZPKR"},"agent_actions":{"view_html":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR","download_json":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR.json","view_paper":"https://pith.science/paper/H3NTZPKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00448&json=true","fetch_graph":"https://pith.science/api/pith-number/H3NTZPKRQZ6KI3AA3HBHLEYESR/graph.json","fetch_events":"https://pith.science/api/pith-number/H3NTZPKRQZ6KI3AA3HBHLEYESR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR/action/storage_attestation","attest_author":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR/action/author_attestation","sign_citation":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR/action/citation_signature","submit_replication":"https://pith.science/pith/H3NTZPKRQZ6KI3AA3HBHLEYESR/action/replication_record"}},"created_at":"2026-07-05T10:08:33.826927+00:00","updated_at":"2026-07-05T10:08:33.826927+00:00"}