{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IEAI7A3NQWGUD5PTJBC2AXJBBB","short_pith_number":"pith:IEAI7A3N","canonical_record":{"source":{"id":"2112.07899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-15T05:33:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f2bbe5dcd37d2340b78a6ed8554b90c9f00bb82b01df020ba5b4e71bacf052a","abstract_canon_sha256":"2e9b04d4ba56455421591fda61c0e3818d0663a0fc17c5552675c0380fb3a2d1"},"schema_version":"1.0"},"canonical_sha256":"41008f836d858d41f5f34845a05d21084e9e13760063d08b7e5fd0a5ac74e06e","source":{"kind":"arxiv","id":"2112.07899","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07899","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07899v1","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07899","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"pith_short_12","alias_value":"IEAI7A3NQWGU","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"pith_short_16","alias_value":"IEAI7A3NQWGUD5PT","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"pith_short_8","alias_value":"IEAI7A3N","created_at":"2026-07-05T03:41:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IEAI7A3NQWGUD5PTJBC2AXJBBB","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-15T05:33:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f2bbe5dcd37d2340b78a6ed8554b90c9f00bb82b01df020ba5b4e71bacf052a","abstract_canon_sha256":"2e9b04d4ba56455421591fda61c0e3818d0663a0fc17c5552675c0380fb3a2d1"},"schema_version":"1.0"},"canonical_sha256":"41008f836d858d41f5f34845a05d21084e9e13760063d08b7e5fd0a5ac74e06e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:08.206092Z","signature_b64":"r0YYQu2tJnc+LkqcfqM0VaF3l9UQ3py1NG1iig5Vqu8wFLSpSmhkOkHBbw+Qmbzyzo7Tfrad8FOxD+JDPR3fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41008f836d858d41f5f34845a05d21084e9e13760063d08b7e5fd0a5ac74e06e","last_reissued_at":"2026-07-05T03:41:08.205701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:08.205701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07899","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":"2026-07-05T03:41:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ral0WOjJB3bZccjb2bhXjov++dRGTfEuMSE/ZMMNWvWnmJR8JFtdoLWv0HVd0f/ypj3fUaoMLFBn9pCp/1mzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:05:06.833347Z"},"content_sha256":"d8ed6d809509dcaa6b909d57336ed29b90c3f502a02200a83cfdbcfd4619c4bb","schema_version":"1.0","event_id":"sha256:d8ed6d809509dcaa6b909d57336ed29b90c3f502a02200a83cfdbcfd4619c4bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IEAI7A3NQWGUD5PTJBC2AXJBBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Dual Encoders Are Generalizable Retrievers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chen Qu, Gustavo Hern\\'andez \\'Abrego, Jianmo Ni, Ji Ma, Jing Lu, Keith B. Hall, Ming-Wei Chang, Vincent Y. Zhao, Yi Luan, Yinfei Yang, Zhuyun Dai","submitted_at":"2021-12-15T05:33:27Z","abstract_excerpt":"It has been shown that dual encoders trained on one domain often fail to generalize to other domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual encoder, where the final score is simply a dot-product between a query vector and a passage vector, is too limited to make dual encoders an effective retrieval model for out-of-domain generalization. In this paper, we challenge this belief by scaling up the size of the dual encoder model {\\em while keeping the bottleneck embedding size fixed.} With multi-stage training, surprisingly, scaling up the model size brin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07899","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/2112.07899/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":"2026-07-05T03:41:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yLmniKZSYBUxeUZAfBlHBA/mYxWnyBFH/dDONWuM03HraJuiL6oyRFtEDEWcglHZ6RcDQtSO7sXzfjjKuFthCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:05:06.833856Z"},"content_sha256":"d63353391bd63c5170627f22e095082e8aa23231eecdbbe69393ae838c3dc7df","schema_version":"1.0","event_id":"sha256:d63353391bd63c5170627f22e095082e8aa23231eecdbbe69393ae838c3dc7df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB/bundle.json","state_url":"https://pith.science/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB/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":"2026-08-05T14:05:06Z","links":{"resolver":"https://pith.science/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB","bundle":"https://pith.science/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB/bundle.json","state":"https://pith.science/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEAI7A3NQWGUD5PTJBC2AXJBBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IEAI7A3NQWGUD5PTJBC2AXJBBB","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":"2e9b04d4ba56455421591fda61c0e3818d0663a0fc17c5552675c0380fb3a2d1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-15T05:33:27Z","title_canon_sha256":"4f2bbe5dcd37d2340b78a6ed8554b90c9f00bb82b01df020ba5b4e71bacf052a"},"schema_version":"1.0","source":{"id":"2112.07899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07899","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07899v1","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07899","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"pith_short_12","alias_value":"IEAI7A3NQWGU","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"pith_short_16","alias_value":"IEAI7A3NQWGUD5PT","created_at":"2026-07-05T03:41:08Z"},{"alias_kind":"pith_short_8","alias_value":"IEAI7A3N","created_at":"2026-07-05T03:41:08Z"}],"graph_snapshots":[{"event_id":"sha256:d63353391bd63c5170627f22e095082e8aa23231eecdbbe69393ae838c3dc7df","target":"graph","created_at":"2026-07-05T03:41:08Z","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/2112.07899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has been shown that dual encoders trained on one domain often fail to generalize to other domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual encoder, where the final score is simply a dot-product between a query vector and a passage vector, is too limited to make dual encoders an effective retrieval model for out-of-domain generalization. In this paper, we challenge this belief by scaling up the size of the dual encoder model {\\em while keeping the bottleneck embedding size fixed.} With multi-stage training, surprisingly, scaling up the model size brin","authors_text":"Chen Qu, Gustavo Hern\\'andez \\'Abrego, Jianmo Ni, Ji Ma, Jing Lu, Keith B. Hall, Ming-Wei Chang, Vincent Y. Zhao, Yi Luan, Yinfei Yang, Zhuyun Dai","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-15T05:33:27Z","title":"Large Dual Encoders Are Generalizable Retrievers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07899","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:d8ed6d809509dcaa6b909d57336ed29b90c3f502a02200a83cfdbcfd4619c4bb","target":"record","created_at":"2026-07-05T03:41:08Z","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":"2e9b04d4ba56455421591fda61c0e3818d0663a0fc17c5552675c0380fb3a2d1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-15T05:33:27Z","title_canon_sha256":"4f2bbe5dcd37d2340b78a6ed8554b90c9f00bb82b01df020ba5b4e71bacf052a"},"schema_version":"1.0","source":{"id":"2112.07899","kind":"arxiv","version":1}},"canonical_sha256":"41008f836d858d41f5f34845a05d21084e9e13760063d08b7e5fd0a5ac74e06e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41008f836d858d41f5f34845a05d21084e9e13760063d08b7e5fd0a5ac74e06e","first_computed_at":"2026-07-05T03:41:08.205701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:08.205701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r0YYQu2tJnc+LkqcfqM0VaF3l9UQ3py1NG1iig5Vqu8wFLSpSmhkOkHBbw+Qmbzyzo7Tfrad8FOxD+JDPR3fCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:08.206092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8ed6d809509dcaa6b909d57336ed29b90c3f502a02200a83cfdbcfd4619c4bb","sha256:d63353391bd63c5170627f22e095082e8aa23231eecdbbe69393ae838c3dc7df"],"state_sha256":"f0482f203d124a1bb8daf0083da36c458dd95969ae1d11faabf7465cf6fb1496"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hz4O8qAozWUESGhK98tUHWMNpiG0wVU0tcz3TxzLGWlEdOEteM3ie12I2qWm/E/H/cxwQwu3kDSIdH8cMntIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:05:06.838047Z","bundle_sha256":"a4273ae4ebebc568fed3a1b8ca247bfc8f17f1bc7c82e3c844dfae761f4ca1bb"}}