{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LDN4UA7UVDBXT6VRNO7MU254DG","short_pith_number":"pith:LDN4UA7U","schema_version":"1.0","canonical_sha256":"58dbca03f4a8c379fab16bbeca6bbc19b86e468dbc84417dde3dc6f799d12e9d","source":{"kind":"arxiv","id":"2504.12972","version":1},"attestation_state":"computed","paper":{"title":"Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adithya Pratapa, Teruko Mitamura","submitted_at":"2025-04-17T14:24:51Z","abstract_excerpt":"Recent advances in long-context reasoning abilities of language models led to interesting applications in large-scale multi-document summarization. However, prior work has shown that these long-context models are not effective at their claimed context windows. To this end, retrieval-augmented systems provide an efficient and effective alternative. However, their performance can be highly sensitive to the choice of retrieval context length. In this work, we present a hybrid method that combines retrieval-augmented systems with long-context windows supported by recent language models. Our method"},"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":"2504.12972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T14:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"cec926ff941945a5629fc2ff1769978fbf31ccc7068756f90c7d15df65be3255","abstract_canon_sha256":"e171a68ad98b73c40269a670c2a4194303dbbfcb85582af680c072fa271e75f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:35.641143Z","signature_b64":"4QNPah+RKqJ8m6Hn47xPzHI5E9w+Y07yNm4WPMY63eWyX+94qI2J5TYh8ou2gu246pHO3TnqA/ZOr5p/wtwpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58dbca03f4a8c379fab16bbeca6bbc19b86e468dbc84417dde3dc6f799d12e9d","last_reissued_at":"2026-07-05T10:50:35.640615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:35.640615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adithya Pratapa, Teruko Mitamura","submitted_at":"2025-04-17T14:24:51Z","abstract_excerpt":"Recent advances in long-context reasoning abilities of language models led to interesting applications in large-scale multi-document summarization. However, prior work has shown that these long-context models are not effective at their claimed context windows. To this end, retrieval-augmented systems provide an efficient and effective alternative. However, their performance can be highly sensitive to the choice of retrieval context length. In this work, we present a hybrid method that combines retrieval-augmented systems with long-context windows supported by recent language models. Our method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12972","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/2504.12972/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":"2504.12972","created_at":"2026-07-05T10:50:35.640674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12972v1","created_at":"2026-07-05T10:50:35.640674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12972","created_at":"2026-07-05T10:50:35.640674+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDN4UA7UVDBX","created_at":"2026-07-05T10:50:35.640674+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDN4UA7UVDBXT6VR","created_at":"2026-07-05T10:50:35.640674+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDN4UA7U","created_at":"2026-07-05T10:50:35.640674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG","json":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG.json","graph_json":"https://pith.science/api/pith-number/LDN4UA7UVDBXT6VRNO7MU254DG/graph.json","events_json":"https://pith.science/api/pith-number/LDN4UA7UVDBXT6VRNO7MU254DG/events.json","paper":"https://pith.science/paper/LDN4UA7U"},"agent_actions":{"view_html":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG","download_json":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG.json","view_paper":"https://pith.science/paper/LDN4UA7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12972&json=true","fetch_graph":"https://pith.science/api/pith-number/LDN4UA7UVDBXT6VRNO7MU254DG/graph.json","fetch_events":"https://pith.science/api/pith-number/LDN4UA7UVDBXT6VRNO7MU254DG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG/action/storage_attestation","attest_author":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG/action/author_attestation","sign_citation":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG/action/citation_signature","submit_replication":"https://pith.science/pith/LDN4UA7UVDBXT6VRNO7MU254DG/action/replication_record"}},"created_at":"2026-07-05T10:50:35.640674+00:00","updated_at":"2026-07-05T10:50:35.640674+00:00"}