{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QOUENK32YSLK3QIUDZRBXU6WEJ","short_pith_number":"pith:QOUENK32","canonical_record":{"source":{"id":"2210.13678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-25T00:53:06Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"ddf97958b2ee2516d4f03c2958040efa327d5c098922d1672a48ead5caa52efb","abstract_canon_sha256":"281d9b9b5f69e00411763ea90a19a9c7e1189f298cf32b6fafc80d1ea03a90d0"},"schema_version":"1.0"},"canonical_sha256":"83a846ab7ac496adc1141e621bd3d622521836e426155d35d38ac8ec92f9d4fc","source":{"kind":"arxiv","id":"2210.13678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13678","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13678v1","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13678","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"QOUENK32YSLK","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"QOUENK32YSLK3QIU","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"QOUENK32","created_at":"2026-07-05T05:10:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QOUENK32YSLK3QIUDZRBXU6WEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.13678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-25T00:53:06Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"ddf97958b2ee2516d4f03c2958040efa327d5c098922d1672a48ead5caa52efb","abstract_canon_sha256":"281d9b9b5f69e00411763ea90a19a9c7e1189f298cf32b6fafc80d1ea03a90d0"},"schema_version":"1.0"},"canonical_sha256":"83a846ab7ac496adc1141e621bd3d622521836e426155d35d38ac8ec92f9d4fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:20.912751Z","signature_b64":"FrdxpdZXtW+oDVaLfQwTUu7toYv9d11MfhKk3H6L9f2HrH2U3fRePIHWmFvdrRmJBXWLU3P6FGSNF9XzKBEYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a846ab7ac496adc1141e621bd3d622521836e426155d35d38ac8ec92f9d4fc","last_reissued_at":"2026-07-05T05:10:20.912297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:20.912297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.13678","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":"2026-07-05T05:10:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPg6nPCbNr+SOVKfiu01QKQwS8myPXVzdiFhvs3BhBeHgQtYnUOl9zzkPEUVoEmWuZTg4YHNrWxTI8YS5rF1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:50:08.717925Z"},"content_sha256":"3f29daca0f947e00cbc3991b4d8702975baabca04b8c8f3d85f0f0d4b0607764","schema_version":"1.0","event_id":"sha256:3f29daca0f947e00cbc3991b4d8702975baabca04b8c8f3d85f0f0d4b0607764"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QOUENK32YSLK3QIUDZRBXU6WEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Training-Inference Gap for Dense Phrase Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Barlas Oguz, Gyuwan Kim, Jinhyuk Lee, Wenhan Xiong, William Yang Wang, Yashar Mehdad, Yizhe Zhang","submitted_at":"2022-10-25T00:53:06Z","abstract_excerpt":"Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not exactly reflect the retrieval scenario at inference time. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced, focusing on dense phrase retrieval (Lee et al., 2021) where billions of representations are indexed at inference. Since validating every dense retriever with a large-scale index is practically infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13678","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/2210.13678/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":"2026-07-05T05:10:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cEXVBzGQzSig9NSGz9QeLU+VpHoiKa4RWf50XwyDDJX5Ed3GzOMZtIdsxmHagIMEWxNBiVfADsCeAX3Ux/OHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:50:08.718435Z"},"content_sha256":"a572fb7b9e00f54a00c6660c2e1f62a75cffdc58904791dde95d8750079da2a4","schema_version":"1.0","event_id":"sha256:a572fb7b9e00f54a00c6660c2e1f62a75cffdc58904791dde95d8750079da2a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOUENK32YSLK3QIUDZRBXU6WEJ/bundle.json","state_url":"https://pith.science/pith/QOUENK32YSLK3QIUDZRBXU6WEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOUENK32YSLK3QIUDZRBXU6WEJ/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":"2026-08-05T19:50:08Z","links":{"resolver":"https://pith.science/pith/QOUENK32YSLK3QIUDZRBXU6WEJ","bundle":"https://pith.science/pith/QOUENK32YSLK3QIUDZRBXU6WEJ/bundle.json","state":"https://pith.science/pith/QOUENK32YSLK3QIUDZRBXU6WEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOUENK32YSLK3QIUDZRBXU6WEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QOUENK32YSLK3QIUDZRBXU6WEJ","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":"281d9b9b5f69e00411763ea90a19a9c7e1189f298cf32b6fafc80d1ea03a90d0","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-25T00:53:06Z","title_canon_sha256":"ddf97958b2ee2516d4f03c2958040efa327d5c098922d1672a48ead5caa52efb"},"schema_version":"1.0","source":{"id":"2210.13678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13678","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13678v1","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13678","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"QOUENK32YSLK","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"QOUENK32YSLK3QIU","created_at":"2026-07-05T05:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"QOUENK32","created_at":"2026-07-05T05:10:20Z"}],"graph_snapshots":[{"event_id":"sha256:a572fb7b9e00f54a00c6660c2e1f62a75cffdc58904791dde95d8750079da2a4","target":"graph","created_at":"2026-07-05T05:10:20Z","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/2210.13678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not exactly reflect the retrieval scenario at inference time. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced, focusing on dense phrase retrieval (Lee et al., 2021) where billions of representations are indexed at inference. Since validating every dense retriever with a large-scale index is practically infe","authors_text":"Barlas Oguz, Gyuwan Kim, Jinhyuk Lee, Wenhan Xiong, William Yang Wang, Yashar Mehdad, Yizhe Zhang","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-25T00:53:06Z","title":"Bridging the Training-Inference Gap for Dense Phrase Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13678","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":"sha256:3f29daca0f947e00cbc3991b4d8702975baabca04b8c8f3d85f0f0d4b0607764","target":"record","created_at":"2026-07-05T05:10:20Z","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":"281d9b9b5f69e00411763ea90a19a9c7e1189f298cf32b6fafc80d1ea03a90d0","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-25T00:53:06Z","title_canon_sha256":"ddf97958b2ee2516d4f03c2958040efa327d5c098922d1672a48ead5caa52efb"},"schema_version":"1.0","source":{"id":"2210.13678","kind":"arxiv","version":1}},"canonical_sha256":"83a846ab7ac496adc1141e621bd3d622521836e426155d35d38ac8ec92f9d4fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83a846ab7ac496adc1141e621bd3d622521836e426155d35d38ac8ec92f9d4fc","first_computed_at":"2026-07-05T05:10:20.912297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:20.912297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FrdxpdZXtW+oDVaLfQwTUu7toYv9d11MfhKk3H6L9f2HrH2U3fRePIHWmFvdrRmJBXWLU3P6FGSNF9XzKBEYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:20.912751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f29daca0f947e00cbc3991b4d8702975baabca04b8c8f3d85f0f0d4b0607764","sha256:a572fb7b9e00f54a00c6660c2e1f62a75cffdc58904791dde95d8750079da2a4"],"state_sha256":"e7a755720b01ec272f1b734b130e776a174152c786e628309efd25a9c34abf7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2KiALwHrShI/+gcfAP3fBk18THlzJBJucm+cTHm3b0s7r87Ehu7C3DmVaqeyVOV0OJcaFbiYG78mQkzKA3sCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:50:08.723006Z","bundle_sha256":"c8a33865632ea43ed3c59bb878de0b2a9ee7143cf668b0ce2eaee6c27140276f"}}