{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T3IZHHWCUM7NCCEHSPTDRNTDS5","short_pith_number":"pith:T3IZHHWC","schema_version":"1.0","canonical_sha256":"9ed1939ec2a33ed1088793e638b663976d16727b7d5345e23b9bdbe4cca158f9","source":{"kind":"arxiv","id":"2410.11119","version":5},"attestation_state":"computed","paper":{"title":"ChuLo: Chunk-Level Key Information Representation for Long Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feiqi Cao, Soyeon Caren Han, Yan Li, Yue Dai","submitted_at":"2024-10-14T22:06:54Z","abstract_excerpt":"Transformer-based models have achieved remarkable success in various Natural Language Processing (NLP) tasks, yet their ability to handle long documents is constrained by computational limitations. Traditional approaches, such as truncating inputs, sparse self-attention, and chunking, attempt to mitigate these issues, but they often lead to information loss and hinder the model's ability to capture long-range dependencies. In this paper, we introduce ChuLo, a novel chunk representation method for long document understanding that addresses these limitations. Our ChuLo groups input tokens using "},"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":"2410.11119","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T22:06:54Z","cross_cats_sorted":[],"title_canon_sha256":"89f652664db5c4096070ff3b5d8d7b83ca9e99233161275fce7f8802de16274e","abstract_canon_sha256":"c11cc020a33087c462ebd254f5f9e67e48b020f40c0ee57c841ad9f9c33b1213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:15.826541Z","signature_b64":"C/ALZaeK6+QaCZES2hUQMEfx+6avS8OBxrj7pjN7EfrJoIdaI8m675Ql6FClCPcSZlHFXkpLrcgZD6asdqNCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ed1939ec2a33ed1088793e638b663976d16727b7d5345e23b9bdbe4cca158f9","last_reissued_at":"2026-07-05T11:56:15.825834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:15.825834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChuLo: Chunk-Level Key Information Representation for Long Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feiqi Cao, Soyeon Caren Han, Yan Li, Yue Dai","submitted_at":"2024-10-14T22:06:54Z","abstract_excerpt":"Transformer-based models have achieved remarkable success in various Natural Language Processing (NLP) tasks, yet their ability to handle long documents is constrained by computational limitations. Traditional approaches, such as truncating inputs, sparse self-attention, and chunking, attempt to mitigate these issues, but they often lead to information loss and hinder the model's ability to capture long-range dependencies. In this paper, we introduce ChuLo, a novel chunk representation method for long document understanding that addresses these limitations. Our ChuLo groups input tokens using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11119","kind":"arxiv","version":5},"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/2410.11119/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":"2410.11119","created_at":"2026-07-05T11:56:15.825930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11119v5","created_at":"2026-07-05T11:56:15.825930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11119","created_at":"2026-07-05T11:56:15.825930+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3IZHHWCUM7N","created_at":"2026-07-05T11:56:15.825930+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3IZHHWCUM7NCCEH","created_at":"2026-07-05T11:56:15.825930+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3IZHHWC","created_at":"2026-07-05T11:56:15.825930+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/T3IZHHWCUM7NCCEHSPTDRNTDS5","json":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5.json","graph_json":"https://pith.science/api/pith-number/T3IZHHWCUM7NCCEHSPTDRNTDS5/graph.json","events_json":"https://pith.science/api/pith-number/T3IZHHWCUM7NCCEHSPTDRNTDS5/events.json","paper":"https://pith.science/paper/T3IZHHWC"},"agent_actions":{"view_html":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5","download_json":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5.json","view_paper":"https://pith.science/paper/T3IZHHWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11119&json=true","fetch_graph":"https://pith.science/api/pith-number/T3IZHHWCUM7NCCEHSPTDRNTDS5/graph.json","fetch_events":"https://pith.science/api/pith-number/T3IZHHWCUM7NCCEHSPTDRNTDS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5/action/storage_attestation","attest_author":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5/action/author_attestation","sign_citation":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5/action/citation_signature","submit_replication":"https://pith.science/pith/T3IZHHWCUM7NCCEHSPTDRNTDS5/action/replication_record"}},"created_at":"2026-07-05T11:56:15.825930+00:00","updated_at":"2026-07-05T11:56:15.825930+00:00"}