{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KETWXBVXFBGVFB6UGGTEE4IFSL","short_pith_number":"pith:KETWXBVX","schema_version":"1.0","canonical_sha256":"51276b86b7284d5287d431a642710592ff5c864d1618356beb477c19f14e288f","source":{"kind":"arxiv","id":"2607.16209","version":1},"attestation_state":"computed","paper":{"title":"Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongsheng Hou, Yanqiao Chen, Yepang Liu, Yuhan Rui, Zhen Cao","submitted_at":"2026-05-10T13:27:01Z","abstract_excerpt":"Context reranking and pruning have become essential for improving the efficiency of modern Retrieval-Augmented Generation (RAG) systems, yet an interpretable and unified framework remains underexplored. Previous work has primarily emphasized lexical retrieval, cross-encoder architectures, model distillation, and Low-Rank Adaptation (LoRA), mostly relying on heuristic loss functions and empirical attribution. This paper presents Shapley Context Pruning (SCP), a novel framework for context reranking that establishes a cooperative-game-theory perspective for importance attribution by modeling the"},"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":"2607.16209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-10T13:27:01Z","cross_cats_sorted":[],"title_canon_sha256":"ea8d066be9ef570b959ccc66edc24459f24e127c47690a705f7731b5161031a8","abstract_canon_sha256":"0501a5c5569d319cec811ec254f59258e3d853193a59f3d13571aadc72ccc87d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:05.847037Z","signature_b64":"dNz1acfUowtd4Y35KYxH6J4PEikDhVqGvhijpAQHNy+pdDwHM2vwJgvi/JeUQV1K8uo7Ua2mbAqWqFFZswJLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51276b86b7284d5287d431a642710592ff5c864d1618356beb477c19f14e288f","last_reissued_at":"2026-07-21T00:20:05.846089Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:05.846089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongsheng Hou, Yanqiao Chen, Yepang Liu, Yuhan Rui, Zhen Cao","submitted_at":"2026-05-10T13:27:01Z","abstract_excerpt":"Context reranking and pruning have become essential for improving the efficiency of modern Retrieval-Augmented Generation (RAG) systems, yet an interpretable and unified framework remains underexplored. Previous work has primarily emphasized lexical retrieval, cross-encoder architectures, model distillation, and Low-Rank Adaptation (LoRA), mostly relying on heuristic loss functions and empirical attribution. This paper presents Shapley Context Pruning (SCP), a novel framework for context reranking that establishes a cooperative-game-theory perspective for importance attribution by modeling the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16209","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/2607.16209/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":"2607.16209","created_at":"2026-07-21T00:20:05.846565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16209v1","created_at":"2026-07-21T00:20:05.846565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16209","created_at":"2026-07-21T00:20:05.846565+00:00"},{"alias_kind":"pith_short_12","alias_value":"KETWXBVXFBGV","created_at":"2026-07-21T00:20:05.846565+00:00"},{"alias_kind":"pith_short_16","alias_value":"KETWXBVXFBGVFB6U","created_at":"2026-07-21T00:20:05.846565+00:00"},{"alias_kind":"pith_short_8","alias_value":"KETWXBVX","created_at":"2026-07-21T00:20:05.846565+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/KETWXBVXFBGVFB6UGGTEE4IFSL","json":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL.json","graph_json":"https://pith.science/api/pith-number/KETWXBVXFBGVFB6UGGTEE4IFSL/graph.json","events_json":"https://pith.science/api/pith-number/KETWXBVXFBGVFB6UGGTEE4IFSL/events.json","paper":"https://pith.science/paper/KETWXBVX"},"agent_actions":{"view_html":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL","download_json":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL.json","view_paper":"https://pith.science/paper/KETWXBVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16209&json=true","fetch_graph":"https://pith.science/api/pith-number/KETWXBVXFBGVFB6UGGTEE4IFSL/graph.json","fetch_events":"https://pith.science/api/pith-number/KETWXBVXFBGVFB6UGGTEE4IFSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL/action/storage_attestation","attest_author":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL/action/author_attestation","sign_citation":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL/action/citation_signature","submit_replication":"https://pith.science/pith/KETWXBVXFBGVFB6UGGTEE4IFSL/action/replication_record"}},"created_at":"2026-07-21T00:20:05.846565+00:00","updated_at":"2026-07-21T00:20:05.846565+00:00"}