{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SNI2FTOGRRLA72X6PVKM7DC23Y","short_pith_number":"pith:SNI2FTOG","schema_version":"1.0","canonical_sha256":"9351a2cdc68c560feafe7d54cf8c5ade3a2071883c3f614dabe7bd4054761d4b","source":{"kind":"arxiv","id":"2407.09014","version":3},"attestation_state":"computed","paper":{"title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanwoong Yoon, Hyeon Hwang, Jaewoo Kang, Minbyul Jeong, Taewhoo Lee","submitted_at":"2024-07-12T06:06:54Z","abstract_excerpt":"Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive doc"},"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":"2407.09014","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T06:06:54Z","cross_cats_sorted":[],"title_canon_sha256":"a53e15335cac18c6029771bbf1758c43f1bec26e00646d8cd5c7ad90a5f817b5","abstract_canon_sha256":"9f44398a2c1426e60cb484ada3ffb3f6a98d6758c44baa2de9aa80288b432dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:01.015657Z","signature_b64":"1QidPunwBXaXATcLSkEjSAvsWrJeK+Aqcv2CPcQ3ORu1k9hykXLCtfwky7UBV99LesiUWDgObjRnaIZ4QNYMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9351a2cdc68c560feafe7d54cf8c5ade3a2071883c3f614dabe7bd4054761d4b","last_reissued_at":"2026-07-05T09:20:01.015201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:01.015201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanwoong Yoon, Hyeon Hwang, Jaewoo Kang, Minbyul Jeong, Taewhoo Lee","submitted_at":"2024-07-12T06:06:54Z","abstract_excerpt":"Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive doc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09014","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/2407.09014/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":"2407.09014","created_at":"2026-07-05T09:20:01.015256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09014v3","created_at":"2026-07-05T09:20:01.015256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09014","created_at":"2026-07-05T09:20:01.015256+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNI2FTOGRRLA","created_at":"2026-07-05T09:20:01.015256+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNI2FTOGRRLA72X6","created_at":"2026-07-05T09:20:01.015256+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNI2FTOG","created_at":"2026-07-05T09:20:01.015256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08032","citing_title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","ref_index":144,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01916","citing_title":"ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09659","citing_title":"End-to-End Context Compression at Scale","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08324","citing_title":"Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23734","citing_title":"Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y","json":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y.json","graph_json":"https://pith.science/api/pith-number/SNI2FTOGRRLA72X6PVKM7DC23Y/graph.json","events_json":"https://pith.science/api/pith-number/SNI2FTOGRRLA72X6PVKM7DC23Y/events.json","paper":"https://pith.science/paper/SNI2FTOG"},"agent_actions":{"view_html":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y","download_json":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y.json","view_paper":"https://pith.science/paper/SNI2FTOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09014&json=true","fetch_graph":"https://pith.science/api/pith-number/SNI2FTOGRRLA72X6PVKM7DC23Y/graph.json","fetch_events":"https://pith.science/api/pith-number/SNI2FTOGRRLA72X6PVKM7DC23Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y/action/storage_attestation","attest_author":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y/action/author_attestation","sign_citation":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y/action/citation_signature","submit_replication":"https://pith.science/pith/SNI2FTOGRRLA72X6PVKM7DC23Y/action/replication_record"}},"created_at":"2026-07-05T09:20:01.015256+00:00","updated_at":"2026-07-05T09:20:01.015256+00:00"}