{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DEDR6O566EDCSOTUVN3CCVFJGG","short_pith_number":"pith:DEDR6O56","canonical_record":{"source":{"id":"2603.17205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-03-17T23:11:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e661b6fb1da2bc829e743ef4e5d597de8bf6d1abf928c37ff88d879dc7c63a7b","abstract_canon_sha256":"a9ccc887523edc0ef9cdb99bc6ae2d94b991076c101b91cb598b4668ae00cf22"},"schema_version":"1.0"},"canonical_sha256":"19071f3bbef106293a74ab762154a931868e3b78f5fd3ebbc21307fa0365a1bf","source":{"kind":"arxiv","id":"2603.17205","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DEDR6O566EDCSOTUVN3CCVFJGG","target":"record","payload":{"canonical_record":{"source":{"id":"2603.17205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-03-17T23:11:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e661b6fb1da2bc829e743ef4e5d597de8bf6d1abf928c37ff88d879dc7c63a7b","abstract_canon_sha256":"a9ccc887523edc0ef9cdb99bc6ae2d94b991076c101b91cb598b4668ae00cf22"},"schema_version":"1.0"},"canonical_sha256":"19071f3bbef106293a74ab762154a931868e3b78f5fd3ebbc21307fa0365a1bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:14:50.565586Z","signature_b64":"tOmNrqarCwW07PmisiEA2s8PlyTKBNbynD/IsQ1sFcxI8Mx5JYGQWJaOcqRA2lX+NsnpommUQ/ZXEUfClbVFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19071f3bbef106293a74ab762154a931868e3b78f5fd3ebbc21307fa0365a1bf","last_reissued_at":"2026-08-03T01:14:50.563985Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:14:50.563985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.17205","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LafbJHW2FICnss4Y4ussKRaBxDKaTN0btziE1PxWCtIhb7PwLQNj8M82n7flPCfzVhQQNoH1qtUWapgkoK26CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:37:51.311857Z"},"content_sha256":"5073107549afb718b2763fc208d2029bb5df86f98068e0ce85af24bebe9c4855","schema_version":"1.0","event_id":"sha256:5073107549afb718b2763fc208d2029bb5df86f98068e0ce85af24bebe9c4855"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DEDR6O566EDCSOTUVN3CCVFJGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bernie Wang, Cuixiong Hu, George Karypis, Haoyang Fang, Hengyi Wang, Katrin Kirchhoff, Shuai Zhang, Yifei Ma","submitted_at":"2026-03-17T23:11:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17205","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/2603.17205/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//yrsQZLHh2c6UZwT7uxHW+Wr4lHJq9upLssoqk1TmgXlMDkb+Dbab0Xp8sU2NGpjqxd+kyWfQH9VY7luncwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:37:51.312400Z"},"content_sha256":"3f56c49eeccfd68f122d64b83823bdb51bb0fe9aaba0633e9f1b7ffa53a0d7cc","schema_version":"1.0","event_id":"sha256:3f56c49eeccfd68f122d64b83823bdb51bb0fe9aaba0633e9f1b7ffa53a0d7cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEDR6O566EDCSOTUVN3CCVFJGG/bundle.json","state_url":"https://pith.science/pith/DEDR6O566EDCSOTUVN3CCVFJGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEDR6O566EDCSOTUVN3CCVFJGG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T15:37:51Z","links":{"resolver":"https://pith.science/pith/DEDR6O566EDCSOTUVN3CCVFJGG","bundle":"https://pith.science/pith/DEDR6O566EDCSOTUVN3CCVFJGG/bundle.json","state":"https://pith.science/pith/DEDR6O566EDCSOTUVN3CCVFJGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEDR6O566EDCSOTUVN3CCVFJGG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GEpXhwmNLEPR/1s3vY5MBNZdRoj4bv/ue3WXe0SoklKsQ7FMeSNUibdTOM41zUHqhjf3tgJ4ylGvVD5oe99kBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:37:51.317256Z","bundle_sha256":"d257d12d5f80d6aadb2d61dba31216c59fef8fa3cbe6ecdebb1696dbfe5fa1f0"}}