{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GEYPE2F54RO7ETGBDXPUQDIYHH","short_pith_number":"pith:GEYPE2F5","canonical_record":{"source":{"id":"2007.00808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-01T23:15:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"555b005abbac6178ab01c17cd261815599964df2c06be23d81af176d10876441","abstract_canon_sha256":"1efd50254258e8be91a5b204910063254dfe8d9ef3322fd9e2089e69f057e85b"},"schema_version":"1.0"},"canonical_sha256":"3130f268bde45df24cc11ddf480d1839f161edf2e7bc1ca3f10af5b709f901c0","source":{"kind":"arxiv","id":"2007.00808","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00808","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00808v2","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00808","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"GEYPE2F54RO7","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"GEYPE2F54RO7ETGB","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"GEYPE2F5","created_at":"2026-07-05T01:44:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GEYPE2F54RO7ETGBDXPUQDIYHH","target":"record","payload":{"canonical_record":{"source":{"id":"2007.00808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-01T23:15:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"555b005abbac6178ab01c17cd261815599964df2c06be23d81af176d10876441","abstract_canon_sha256":"1efd50254258e8be91a5b204910063254dfe8d9ef3322fd9e2089e69f057e85b"},"schema_version":"1.0"},"canonical_sha256":"3130f268bde45df24cc11ddf480d1839f161edf2e7bc1ca3f10af5b709f901c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:49.370581Z","signature_b64":"U8tWTVro716MJlFkiaWEW2Cop1kRCYEvFQZOlngwvzV02o0ARWRk7IFLcBlEXonb0YJ+mS8nGfp8LdNvvWejCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3130f268bde45df24cc11ddf480d1839f161edf2e7bc1ca3f10af5b709f901c0","last_reissued_at":"2026-07-05T01:44:49.370100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:49.370100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.00808","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwbECjAS7IklzEYynAv491JMDZxg75lJlu0+FasNHk/aKohoYF8kIQ9McE5qepkVaAZ+27tNN0K016uQM12bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:07:32.010878Z"},"content_sha256":"48b7d3ec4bc6a085a59bcdaadfe35487381c2b2d23c5e2270d2c7e93c14d7daf","schema_version":"1.0","event_id":"sha256:48b7d3ec4bc6a085a59bcdaadfe35487381c2b2d23c5e2270d2c7e93c14d7daf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GEYPE2F54RO7ETGBDXPUQDIYHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Arnold Overwijk, Chenyan Xiong, Jialin Liu, Junaid Ahmed, Kwok-Fung Tang, Lee Xiong, Paul Bennett, Ye Li","submitted_at":"2020-07-01T23:15:56Z","abstract_excerpt":"Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires combination with sparse retrieval. In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing. This paper presents Approximate nearest neighbor Negative Contrastive Estimation (ANCE), a training mechanism that constructs negatives from an Approximate Nearest Neighbor (ANN) index of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00808","kind":"arxiv","version":2},"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/2007.00808/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":"2026-07-05T01:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DbEYDoHCY6JyrrTkTjs5Vc0kFeS28FRAU60+kosjzx97oe5BMtsTNU+T+AT7zSI3HyqI59u+1wGS8ClCqtLcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:07:32.011245Z"},"content_sha256":"8c19d64baf52cd71c3a3dffdcbdbbbd2610a18fdf9f40f0dfebd16e1690feb7b","schema_version":"1.0","event_id":"sha256:8c19d64baf52cd71c3a3dffdcbdbbbd2610a18fdf9f40f0dfebd16e1690feb7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GEYPE2F54RO7ETGBDXPUQDIYHH/bundle.json","state_url":"https://pith.science/pith/GEYPE2F54RO7ETGBDXPUQDIYHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GEYPE2F54RO7ETGBDXPUQDIYHH/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":"2026-07-06T19:07:32Z","links":{"resolver":"https://pith.science/pith/GEYPE2F54RO7ETGBDXPUQDIYHH","bundle":"https://pith.science/pith/GEYPE2F54RO7ETGBDXPUQDIYHH/bundle.json","state":"https://pith.science/pith/GEYPE2F54RO7ETGBDXPUQDIYHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GEYPE2F54RO7ETGBDXPUQDIYHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GEYPE2F54RO7ETGBDXPUQDIYHH","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":"1efd50254258e8be91a5b204910063254dfe8d9ef3322fd9e2089e69f057e85b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-01T23:15:56Z","title_canon_sha256":"555b005abbac6178ab01c17cd261815599964df2c06be23d81af176d10876441"},"schema_version":"1.0","source":{"id":"2007.00808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00808","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00808v2","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00808","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"GEYPE2F54RO7","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"GEYPE2F54RO7ETGB","created_at":"2026-07-05T01:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"GEYPE2F5","created_at":"2026-07-05T01:44:49Z"}],"graph_snapshots":[{"event_id":"sha256:8c19d64baf52cd71c3a3dffdcbdbbbd2610a18fdf9f40f0dfebd16e1690feb7b","target":"graph","created_at":"2026-07-05T01:44:49Z","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/2007.00808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires combination with sparse retrieval. In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing. This paper presents Approximate nearest neighbor Negative Contrastive Estimation (ANCE), a training mechanism that constructs negatives from an Approximate Nearest Neighbor (ANN) index of the ","authors_text":"Arnold Overwijk, Chenyan Xiong, Jialin Liu, Junaid Ahmed, Kwok-Fung Tang, Lee Xiong, Paul Bennett, Ye Li","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-01T23:15:56Z","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00808","kind":"arxiv","version":2},"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":"sha256:48b7d3ec4bc6a085a59bcdaadfe35487381c2b2d23c5e2270d2c7e93c14d7daf","target":"record","created_at":"2026-07-05T01:44:49Z","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":"1efd50254258e8be91a5b204910063254dfe8d9ef3322fd9e2089e69f057e85b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-01T23:15:56Z","title_canon_sha256":"555b005abbac6178ab01c17cd261815599964df2c06be23d81af176d10876441"},"schema_version":"1.0","source":{"id":"2007.00808","kind":"arxiv","version":2}},"canonical_sha256":"3130f268bde45df24cc11ddf480d1839f161edf2e7bc1ca3f10af5b709f901c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3130f268bde45df24cc11ddf480d1839f161edf2e7bc1ca3f10af5b709f901c0","first_computed_at":"2026-07-05T01:44:49.370100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:49.370100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U8tWTVro716MJlFkiaWEW2Cop1kRCYEvFQZOlngwvzV02o0ARWRk7IFLcBlEXonb0YJ+mS8nGfp8LdNvvWejCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:49.370581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48b7d3ec4bc6a085a59bcdaadfe35487381c2b2d23c5e2270d2c7e93c14d7daf","sha256:8c19d64baf52cd71c3a3dffdcbdbbbd2610a18fdf9f40f0dfebd16e1690feb7b"],"state_sha256":"068179479519d8b84a7b8794f33d31017b19bbf8519cb442927c7d14c697be42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VAuI0qxZYQLrSCF8aTTFDtb8cuFj14ityG0zLkk/3+BxF/QTI+PhKiju7Ki8gntVa093JDATJth0zuL7P/uaDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:07:32.013251Z","bundle_sha256":"c1c846c09e9624d3be3b2f40ca796fab5c891aada1269987561d0bc932670ddf"}}