{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H3HONUK4FTBUVHPIUNWVEZIPJH","short_pith_number":"pith:H3HONUK4","schema_version":"1.0","canonical_sha256":"3ecee6d15c2cc34a9de8a36d52650f49cb0020820f1c4fdf34482354ae08000a","source":{"kind":"arxiv","id":"2305.11944","version":2},"attestation_state":"computed","paper":{"title":"Exploring the Viability of Synthetic Query Generation for Relevance Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Aditi Chaudhary, Karthik Raman, Kazuma Hashimoto, Krishna Srinivasan, Marc Najork, Mike Bendersky","submitted_at":"2023-05-19T18:03:36Z","abstract_excerpt":"Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models which are finetuned using large collections of labeled data. However, in specialized domains such as e-commerce and healthcare, the viability of this approach is limited by the dearth of large in-domain data. To address this paucity, recent methods leverage these powerful models to generate high-quality task and domain-specific synthetic data. Prior work has largely explored synthetic data generation or query generati"},"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":"2305.11944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-19T18:03:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c11af24c70f104f35cdb7d176827db3adcfbe1eb5b87190ed03f993a5621d8bf","abstract_canon_sha256":"3c6b91b0c2b8899dd4a25983f69b20564620a5955ff981c0d5bb69a7789b7650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:31.806211Z","signature_b64":"KqojTRz8ANnPXzhWe5z9GpitYXDRNvDsj/Ix51VQhXEQ3dowAhUn2Zi6AkSFgkhcWBkbV98f3aWeBVx1HAwdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ecee6d15c2cc34a9de8a36d52650f49cb0020820f1c4fdf34482354ae08000a","last_reissued_at":"2026-07-05T06:21:31.805742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:31.805742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Viability of Synthetic Query Generation for Relevance Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Aditi Chaudhary, Karthik Raman, Kazuma Hashimoto, Krishna Srinivasan, Marc Najork, Mike Bendersky","submitted_at":"2023-05-19T18:03:36Z","abstract_excerpt":"Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models which are finetuned using large collections of labeled data. However, in specialized domains such as e-commerce and healthcare, the viability of this approach is limited by the dearth of large in-domain data. To address this paucity, recent methods leverage these powerful models to generate high-quality task and domain-specific synthetic data. Prior work has largely explored synthetic data generation or query generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11944","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/2305.11944/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":"2305.11944","created_at":"2026-07-05T06:21:31.805797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11944v2","created_at":"2026-07-05T06:21:31.805797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11944","created_at":"2026-07-05T06:21:31.805797+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3HONUK4FTBU","created_at":"2026-07-05T06:21:31.805797+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3HONUK4FTBUVHPI","created_at":"2026-07-05T06:21:31.805797+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3HONUK4","created_at":"2026-07-05T06:21:31.805797+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/H3HONUK4FTBUVHPIUNWVEZIPJH","json":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH.json","graph_json":"https://pith.science/api/pith-number/H3HONUK4FTBUVHPIUNWVEZIPJH/graph.json","events_json":"https://pith.science/api/pith-number/H3HONUK4FTBUVHPIUNWVEZIPJH/events.json","paper":"https://pith.science/paper/H3HONUK4"},"agent_actions":{"view_html":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH","download_json":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH.json","view_paper":"https://pith.science/paper/H3HONUK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11944&json=true","fetch_graph":"https://pith.science/api/pith-number/H3HONUK4FTBUVHPIUNWVEZIPJH/graph.json","fetch_events":"https://pith.science/api/pith-number/H3HONUK4FTBUVHPIUNWVEZIPJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH/action/storage_attestation","attest_author":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH/action/author_attestation","sign_citation":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH/action/citation_signature","submit_replication":"https://pith.science/pith/H3HONUK4FTBUVHPIUNWVEZIPJH/action/replication_record"}},"created_at":"2026-07-05T06:21:31.805797+00:00","updated_at":"2026-07-05T06:21:31.805797+00:00"}