{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G4G4F4XFH7U6DHEFE44MYNFUBJ","short_pith_number":"pith:G4G4F4XF","canonical_record":{"source":{"id":"2112.07577","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:34:43Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7c6a983bfb98a58d1b2f5f9b71b249fdc38a4f6b7b967dfea1db97295313e06d","abstract_canon_sha256":"edd2f7ef3ebe1f39dfbe53dcc495bce5a1cd5ec6e1cbca719e6c03294c7f7074"},"schema_version":"1.0"},"canonical_sha256":"370dc2f2e53fe9e19c852738cc34b40a50a7fbcdfe1b2465759d26477e956476","source":{"kind":"arxiv","id":"2112.07577","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07577","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07577v3","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07577","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"G4G4F4XFH7U6","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"G4G4F4XFH7U6DHEF","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"G4G4F4XF","created_at":"2026-07-05T04:17:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G4G4F4XFH7U6DHEFE44MYNFUBJ","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07577","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:34:43Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7c6a983bfb98a58d1b2f5f9b71b249fdc38a4f6b7b967dfea1db97295313e06d","abstract_canon_sha256":"edd2f7ef3ebe1f39dfbe53dcc495bce5a1cd5ec6e1cbca719e6c03294c7f7074"},"schema_version":"1.0"},"canonical_sha256":"370dc2f2e53fe9e19c852738cc34b40a50a7fbcdfe1b2465759d26477e956476","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:19.417410Z","signature_b64":"5e/jlgQJXUJUAdh3PUnYreeXPEdlQH0SscMZV+i6IPkNUiEF1bO6qChU5n5NeEyVaEQAdqaDPb0H7FSV4qQNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370dc2f2e53fe9e19c852738cc34b40a50a7fbcdfe1b2465759d26477e956476","last_reissued_at":"2026-07-05T04:17:19.416956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:19.416956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07577","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":"2026-07-05T04:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7ESshrCnjmhaMgjgbFs21hkUCVMLKEZ4272wbLMQ6xX3qcHzNQ7rE4P59pzYHKv3QqL1n3VaHUnCabjFXDdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:27.439500Z"},"content_sha256":"e999bff16f033ff70913c9591721d5091dc399ec38f0a18c857775fce535b54e","schema_version":"1.0","event_id":"sha256:e999bff16f033ff70913c9591721d5091dc399ec38f0a18c857775fce535b54e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G4G4F4XFH7U6DHEFE44MYNFUBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Kexin Wang, Nandan Thakur, Nils Reimers","submitted_at":"2021-12-14T17:34:43Z","abstract_excerpt":"Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et al., 2021b), the performance of dense retrievers severely degrades under a domain shift. This limits the usage of dense retrieval approaches to only a few domains with large training datasets.\n  In this paper, we propose the novel unsupervised domain adaptation method Generative Pseudo Labeling (GPL), which combines a query generator with pseudo labeling from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07577","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/2112.07577/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":"2026-07-05T04:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UrQ33AfQ9lwDI+J+/1BLOp5odwJXP6ClGPUY6kdv8IO4A+Axj94qtRAGCszNVV3aAxFxyPu/TMcdIfQzdYmbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:27.439874Z"},"content_sha256":"638ea0833db9b8d960b7ff2c257e53153e98d06484a5d1a51b680692b0662a44","schema_version":"1.0","event_id":"sha256:638ea0833db9b8d960b7ff2c257e53153e98d06484a5d1a51b680692b0662a44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ/bundle.json","state_url":"https://pith.science/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ/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":"2026-07-07T10:05:27Z","links":{"resolver":"https://pith.science/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ","bundle":"https://pith.science/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ/bundle.json","state":"https://pith.science/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4G4F4XFH7U6DHEFE44MYNFUBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G4G4F4XFH7U6DHEFE44MYNFUBJ","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":"edd2f7ef3ebe1f39dfbe53dcc495bce5a1cd5ec6e1cbca719e6c03294c7f7074","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:34:43Z","title_canon_sha256":"7c6a983bfb98a58d1b2f5f9b71b249fdc38a4f6b7b967dfea1db97295313e06d"},"schema_version":"1.0","source":{"id":"2112.07577","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07577","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07577v3","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07577","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"G4G4F4XFH7U6","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"G4G4F4XFH7U6DHEF","created_at":"2026-07-05T04:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"G4G4F4XF","created_at":"2026-07-05T04:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:638ea0833db9b8d960b7ff2c257e53153e98d06484a5d1a51b680692b0662a44","target":"graph","created_at":"2026-07-05T04:17:19Z","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/2112.07577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et al., 2021b), the performance of dense retrievers severely degrades under a domain shift. This limits the usage of dense retrieval approaches to only a few domains with large training datasets.\n  In this paper, we propose the novel unsupervised domain adaptation method Generative Pseudo Labeling (GPL), which combines a query generator with pseudo labeling from ","authors_text":"Iryna Gurevych, Kexin Wang, Nandan Thakur, Nils Reimers","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07577","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:e999bff16f033ff70913c9591721d5091dc399ec38f0a18c857775fce535b54e","target":"record","created_at":"2026-07-05T04:17:19Z","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":"edd2f7ef3ebe1f39dfbe53dcc495bce5a1cd5ec6e1cbca719e6c03294c7f7074","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T17:34:43Z","title_canon_sha256":"7c6a983bfb98a58d1b2f5f9b71b249fdc38a4f6b7b967dfea1db97295313e06d"},"schema_version":"1.0","source":{"id":"2112.07577","kind":"arxiv","version":3}},"canonical_sha256":"370dc2f2e53fe9e19c852738cc34b40a50a7fbcdfe1b2465759d26477e956476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"370dc2f2e53fe9e19c852738cc34b40a50a7fbcdfe1b2465759d26477e956476","first_computed_at":"2026-07-05T04:17:19.416956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:19.416956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5e/jlgQJXUJUAdh3PUnYreeXPEdlQH0SscMZV+i6IPkNUiEF1bO6qChU5n5NeEyVaEQAdqaDPb0H7FSV4qQNAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:19.417410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07577","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e999bff16f033ff70913c9591721d5091dc399ec38f0a18c857775fce535b54e","sha256:638ea0833db9b8d960b7ff2c257e53153e98d06484a5d1a51b680692b0662a44"],"state_sha256":"3efe1c5ea1ada40b718e9fe1dc5dc5fc72e8052e32363ad47d075f0fc4aa4191"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0ReDOhGrF6Z6j9GvfwV7uNtyLy4mx/QkAsEvh0oklFYl6Hj2TK5KVe5kMWJ48emwj3+AhqxXnz2SUI+fdduDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:05:27.442202Z","bundle_sha256":"2c58a219e1073a962ccbbe82cd2ae886773ec4f9d6dc95b943d27dcb4454e965"}}