{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XNAHAMJCTFQKPE4WKPGL243FS7","short_pith_number":"pith:XNAHAMJC","canonical_record":{"source":{"id":"2311.03798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T08:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"0242236327ec3e37f7c8b10dd3568100befb5ca69ce700dd4d4374eabfa3667c","abstract_canon_sha256":"befa36b9963470a7d288152ff19b06bc90a189993568b2c3bc4ddedcd6a1cc22"},"schema_version":"1.0"},"canonical_sha256":"bb407031229960a7939653ccbd736597fde0f306b3cccdb6e4e007c598d28d5e","source":{"kind":"arxiv","id":"2311.03798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03798","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03798v1","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03798","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"XNAHAMJCTFQK","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"XNAHAMJCTFQKPE4W","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"XNAHAMJC","created_at":"2026-07-05T07:10:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XNAHAMJCTFQKPE4WKPGL243FS7","target":"record","payload":{"canonical_record":{"source":{"id":"2311.03798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T08:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"0242236327ec3e37f7c8b10dd3568100befb5ca69ce700dd4d4374eabfa3667c","abstract_canon_sha256":"befa36b9963470a7d288152ff19b06bc90a189993568b2c3bc4ddedcd6a1cc22"},"schema_version":"1.0"},"canonical_sha256":"bb407031229960a7939653ccbd736597fde0f306b3cccdb6e4e007c598d28d5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:05.117782Z","signature_b64":"niF6oK3Y95ZRMHt/H3YBlkWO8cXCApsgyuhVtx9bFXEemuwxsptZ5oRJJd5Mqfisr2HEv+6nAdpvt4NK3UkcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb407031229960a7939653ccbd736597fde0f306b3cccdb6e4e007c598d28d5e","last_reissued_at":"2026-07-05T07:10:05.117249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:05.117249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.03798","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rg5NPv/9Cmq9RXX+Mp6gcNYyeC7JJb3WYE9FzAIme3cfldqxehUU2sKbDPHZ99QhNv06WxfhqqFRo1sbowiXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:28:22.383085Z"},"content_sha256":"fe419da67a7d60ab2ef7b1ce5ad56e74ec5a32bb6cd4f612dbbb3de0ebc787e2","schema_version":"1.0","event_id":"sha256:fe419da67a7d60ab2ef7b1ce5ad56e74ec5a32bb6cd4f612dbbb3de0ebc787e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XNAHAMJCTFQKPE4WKPGL243FS7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noisy Pair Corrector for Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daya Guo, Dayiheng Liu, Hang Zhang, Jiancheng Lv, Jian Guo, Xingwei He, Yeyun Gong","submitted_at":"2023-11-07T08:27:14Z","abstract_excerpt":"Most dense retrieval models contain an implicit assumption: the training query-document pairs are exactly matched. Since it is expensive to annotate the corpus manually, training pairs in real-world applications are usually collected automatically, which inevitably introduces mismatched-pair noise. In this paper, we explore an interesting and challenging problem in dense retrieval, how to train an effective model with mismatched-pair noise. To solve this problem, we propose a novel approach called Noisy Pair Corrector (NPC), which consists of a detection module and a correction module. The det"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03798","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/2311.03798/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":"2026-07-05T07:10:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/K9TqUwZf/neMxUQuc4Vfojjn/qhzI2nv/rANJ9WwDk/CJiUdWc9auJ8EB1i442ppGaFajMHMBs9QwkPNNv0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:28:22.383561Z"},"content_sha256":"91fb9a4f58c0807833bb9e7c365da3a9fc01ac40d3fdc6bf654e0098b5625dd2","schema_version":"1.0","event_id":"sha256:91fb9a4f58c0807833bb9e7c365da3a9fc01ac40d3fdc6bf654e0098b5625dd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNAHAMJCTFQKPE4WKPGL243FS7/bundle.json","state_url":"https://pith.science/pith/XNAHAMJCTFQKPE4WKPGL243FS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNAHAMJCTFQKPE4WKPGL243FS7/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":"2026-08-05T00:28:22Z","links":{"resolver":"https://pith.science/pith/XNAHAMJCTFQKPE4WKPGL243FS7","bundle":"https://pith.science/pith/XNAHAMJCTFQKPE4WKPGL243FS7/bundle.json","state":"https://pith.science/pith/XNAHAMJCTFQKPE4WKPGL243FS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNAHAMJCTFQKPE4WKPGL243FS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XNAHAMJCTFQKPE4WKPGL243FS7","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":"befa36b9963470a7d288152ff19b06bc90a189993568b2c3bc4ddedcd6a1cc22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T08:27:14Z","title_canon_sha256":"0242236327ec3e37f7c8b10dd3568100befb5ca69ce700dd4d4374eabfa3667c"},"schema_version":"1.0","source":{"id":"2311.03798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03798","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03798v1","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03798","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"XNAHAMJCTFQK","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"XNAHAMJCTFQKPE4W","created_at":"2026-07-05T07:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"XNAHAMJC","created_at":"2026-07-05T07:10:05Z"}],"graph_snapshots":[{"event_id":"sha256:91fb9a4f58c0807833bb9e7c365da3a9fc01ac40d3fdc6bf654e0098b5625dd2","target":"graph","created_at":"2026-07-05T07:10:05Z","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/2311.03798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most dense retrieval models contain an implicit assumption: the training query-document pairs are exactly matched. Since it is expensive to annotate the corpus manually, training pairs in real-world applications are usually collected automatically, which inevitably introduces mismatched-pair noise. In this paper, we explore an interesting and challenging problem in dense retrieval, how to train an effective model with mismatched-pair noise. To solve this problem, we propose a novel approach called Noisy Pair Corrector (NPC), which consists of a detection module and a correction module. The det","authors_text":"Daya Guo, Dayiheng Liu, Hang Zhang, Jiancheng Lv, Jian Guo, Xingwei He, Yeyun Gong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T08:27:14Z","title":"Noisy Pair Corrector for Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03798","kind":"arxiv","version":1},"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:fe419da67a7d60ab2ef7b1ce5ad56e74ec5a32bb6cd4f612dbbb3de0ebc787e2","target":"record","created_at":"2026-07-05T07:10:05Z","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":"befa36b9963470a7d288152ff19b06bc90a189993568b2c3bc4ddedcd6a1cc22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T08:27:14Z","title_canon_sha256":"0242236327ec3e37f7c8b10dd3568100befb5ca69ce700dd4d4374eabfa3667c"},"schema_version":"1.0","source":{"id":"2311.03798","kind":"arxiv","version":1}},"canonical_sha256":"bb407031229960a7939653ccbd736597fde0f306b3cccdb6e4e007c598d28d5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb407031229960a7939653ccbd736597fde0f306b3cccdb6e4e007c598d28d5e","first_computed_at":"2026-07-05T07:10:05.117249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:05.117249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"niF6oK3Y95ZRMHt/H3YBlkWO8cXCApsgyuhVtx9bFXEemuwxsptZ5oRJJd5Mqfisr2HEv+6nAdpvt4NK3UkcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:05.117782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.03798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe419da67a7d60ab2ef7b1ce5ad56e74ec5a32bb6cd4f612dbbb3de0ebc787e2","sha256:91fb9a4f58c0807833bb9e7c365da3a9fc01ac40d3fdc6bf654e0098b5625dd2"],"state_sha256":"678e3270cc24c5078a33f19a6016a3f812ef5281f6e654e8e39ac7361f0840c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yyh7O81Kx8XIUWJDtMzMPBWW2tjHrcfh45UkkNeJKT6Vv4zfhHzBag+9d4nRIAxGyT0n0/K81/FSlKDlPe+KBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:28:22.387263Z","bundle_sha256":"ca528eb2f00606aa61eb0151bf353af069cdc7fe50540db29c1bf5915f4892bb"}}