{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KSHHNNUUEPWYPUAPKS2QWOWXKB","short_pith_number":"pith:KSHHNNUU","schema_version":"1.0","canonical_sha256":"548e76b69423ed87d00f54b50b3ad7506efd2f87b6fcfbb8eaf902f6d13a8e05","source":{"kind":"arxiv","id":"2204.09248","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Target Domain Supervision for Open Retrieval QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Avirup Sil, Bhavani Iyer, Md Arafat Sultan, Radu Florian, Revanth Gangi Reddy, Rong Zhang, Salim Roukos, Vittorio Castelli","submitted_at":"2022-04-20T06:28:13Z","abstract_excerpt":"Neural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR) -- a state-of-the-art (SOTA) open domain neural retrieval model -- on closed and specialized target domains such as COVID-19, and find that it lags behind standard BM25 in this important real-world setting. To make DPR more robust under domain shift, we explore its fine-tuning with synthetic training examples, which we generate from unlabeled target domain text using a text-to-text generator. In our experiments, this noisy but fully autom"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.09248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-20T06:28:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"bf9876415b501911048a33e205feb954c25cea32494f6811f0119036d1911f31","abstract_canon_sha256":"4555a923e61eb04b9f94608035509241dc78a0e877d2a0a2a67178c25a1fd4ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:22.611009Z","signature_b64":"LkZJofr/oPW0gMU+h5p2vd5LjyTV2rWArKoPyYg24tUmBwWotZHlsmHjnYtgGl587sJZk08g7Yj3Hn/4Qaz1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548e76b69423ed87d00f54b50b3ad7506efd2f87b6fcfbb8eaf902f6d13a8e05","last_reissued_at":"2026-07-05T04:16:22.610622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:22.610622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Target Domain Supervision for Open Retrieval QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Avirup Sil, Bhavani Iyer, Md Arafat Sultan, Radu Florian, Revanth Gangi Reddy, Rong Zhang, Salim Roukos, Vittorio Castelli","submitted_at":"2022-04-20T06:28:13Z","abstract_excerpt":"Neural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR) -- a state-of-the-art (SOTA) open domain neural retrieval model -- on closed and specialized target domains such as COVID-19, and find that it lags behind standard BM25 in this important real-world setting. To make DPR more robust under domain shift, we explore its fine-tuning with synthetic training examples, which we generate from unlabeled target domain text using a text-to-text generator. In our experiments, this noisy but fully autom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09248","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/2204.09248/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.09248","created_at":"2026-07-05T04:16:22.610681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09248v1","created_at":"2026-07-05T04:16:22.610681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09248","created_at":"2026-07-05T04:16:22.610681+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSHHNNUUEPWY","created_at":"2026-07-05T04:16:22.610681+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSHHNNUUEPWYPUAP","created_at":"2026-07-05T04:16:22.610681+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSHHNNUU","created_at":"2026-07-05T04:16:22.610681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB","json":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB.json","graph_json":"https://pith.science/api/pith-number/KSHHNNUUEPWYPUAPKS2QWOWXKB/graph.json","events_json":"https://pith.science/api/pith-number/KSHHNNUUEPWYPUAPKS2QWOWXKB/events.json","paper":"https://pith.science/paper/KSHHNNUU"},"agent_actions":{"view_html":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB","download_json":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB.json","view_paper":"https://pith.science/paper/KSHHNNUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09248&json=true","fetch_graph":"https://pith.science/api/pith-number/KSHHNNUUEPWYPUAPKS2QWOWXKB/graph.json","fetch_events":"https://pith.science/api/pith-number/KSHHNNUUEPWYPUAPKS2QWOWXKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB/action/storage_attestation","attest_author":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB/action/author_attestation","sign_citation":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB/action/citation_signature","submit_replication":"https://pith.science/pith/KSHHNNUUEPWYPUAPKS2QWOWXKB/action/replication_record"}},"created_at":"2026-07-05T04:16:22.610681+00:00","updated_at":"2026-07-05T04:16:22.610681+00:00"}