{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DEDR6O566EDCSOTUVN3CCVFJGG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a9ccc887523edc0ef9cdb99bc6ae2d94b991076c101b91cb598b4668ae00cf22","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-03-17T23:11:45Z","title_canon_sha256":"e661b6fb1da2bc829e743ef4e5d597de8bf6d1abf928c37ff88d879dc7c63a7b"},"schema_version":"1.0","source":{"id":"2603.17205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.17205","created_at":"2026-08-03T01:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2603.17205v3","created_at":"2026-08-03T01:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17205","created_at":"2026-08-03T01:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"DEDR6O566EDC","created_at":"2026-08-03T01:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"DEDR6O566EDCSOTU","created_at":"2026-08-03T01:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"DEDR6O56","created_at":"2026-08-03T01:14:50Z"}],"graph_snapshots":[{"event_id":"sha256:3f56c49eeccfd68f122d64b83823bdb51bb0fe9aaba0633e9f1b7ffa53a0d7cc","target":"graph","created_at":"2026-08-03T01:14:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.17205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Domain-specific finetuning is essential for dense retrievers, yet not all data pairs contribute equally to the learning process. We introduce OPERA, a data pruning framework that exploits this heterogeneity to improve both the effectiveness and efficiency of retrieval model adaptation. We first investigate static pruning (SP), which retains only high-similarity query-document pairs, revealing an intrinsic quality-coverage tradeoff: ranking (NDCG) improves while retrieval (Recall) can degrade due to reduced query diversity. To resolve this tradeoff, we propose a two-stage dynamic pruning (DP) s","authors_text":"Bernie Wang, Cuixiong Hu, George Karypis, Haoyang Fang, Hengyi Wang, Katrin Kirchhoff, Shuai Zhang, Yifei Ma","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-03-17T23:11:45Z","title":"OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17205","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5073107549afb718b2763fc208d2029bb5df86f98068e0ce85af24bebe9c4855","target":"record","created_at":"2026-08-03T01:14:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a9ccc887523edc0ef9cdb99bc6ae2d94b991076c101b91cb598b4668ae00cf22","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-03-17T23:11:45Z","title_canon_sha256":"e661b6fb1da2bc829e743ef4e5d597de8bf6d1abf928c37ff88d879dc7c63a7b"},"schema_version":"1.0","source":{"id":"2603.17205","kind":"arxiv","version":3}},"canonical_sha256":"19071f3bbef106293a74ab762154a931868e3b78f5fd3ebbc21307fa0365a1bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19071f3bbef106293a74ab762154a931868e3b78f5fd3ebbc21307fa0365a1bf","first_computed_at":"2026-08-03T01:14:50.563985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:14:50.563985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tOmNrqarCwW07PmisiEA2s8PlyTKBNbynD/IsQ1sFcxI8Mx5JYGQWJaOcqRA2lX+NsnpommUQ/ZXEUfClbVFCg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:14:50.565586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.17205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5073107549afb718b2763fc208d2029bb5df86f98068e0ce85af24bebe9c4855","sha256:3f56c49eeccfd68f122d64b83823bdb51bb0fe9aaba0633e9f1b7ffa53a0d7cc"],"state_sha256":"4fce8c7f474f7a2e0d87d4cde879c1d4a072d1372209a4e4eb21518242c851fb"}