{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DYRZAM5EAUT2DMZ4QACJNWZDRU","short_pith_number":"pith:DYRZAM5E","schema_version":"1.0","canonical_sha256":"1e239033a40527a1b33c800496db238d10a9c69ee9fb3190fe2c0817417147e6","source":{"kind":"arxiv","id":"2505.19307","version":1},"attestation_state":"computed","paper":{"title":"Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bruno Martins, Chenyan Xiong, Jo\\~ao Coelho, Jo\\~ao Magalh\\~aes","submitted_at":"2025-05-25T20:34:12Z","abstract_excerpt":"Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic queries generated by large language models offer a scalable alternative. Still, synthetic training queries often vary in quality, which leads to suboptimal downstream retrieval performance. Existing methods typically filter out noisy query-document pairs based on signals from an external re-ranker. In contrast, we propose a framework that leverages Direct P"},"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":"2505.19307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T20:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"f8c1f7f6b6865be58dab8937773b63371c6c4b7f986908d5b912beb797f1bd6a","abstract_canon_sha256":"84feda14c0f11ba3006466b80f8b53958896161ec402ae63eb7c75cd94fb0739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:27.979025Z","signature_b64":"HDoO6rVPfzOOeax34uqrprn4CHy6tDXGlvavZNAnxe5evto8zugFDieXXxd9SQKbFPxO/rAu3qLavopEFd09CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e239033a40527a1b33c800496db238d10a9c69ee9fb3190fe2c0817417147e6","last_reissued_at":"2026-07-05T11:09:27.977507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:27.977507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bruno Martins, Chenyan Xiong, Jo\\~ao Coelho, Jo\\~ao Magalh\\~aes","submitted_at":"2025-05-25T20:34:12Z","abstract_excerpt":"Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic queries generated by large language models offer a scalable alternative. Still, synthetic training queries often vary in quality, which leads to suboptimal downstream retrieval performance. Existing methods typically filter out noisy query-document pairs based on signals from an external re-ranker. In contrast, we propose a framework that leverages Direct P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19307","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/2505.19307/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":"2505.19307","created_at":"2026-07-05T11:09:27.977571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19307v1","created_at":"2026-07-05T11:09:27.977571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19307","created_at":"2026-07-05T11:09:27.977571+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYRZAM5EAUT2","created_at":"2026-07-05T11:09:27.977571+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYRZAM5EAUT2DMZ4","created_at":"2026-07-05T11:09:27.977571+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYRZAM5E","created_at":"2026-07-05T11:09:27.977571+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/DYRZAM5EAUT2DMZ4QACJNWZDRU","json":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU.json","graph_json":"https://pith.science/api/pith-number/DYRZAM5EAUT2DMZ4QACJNWZDRU/graph.json","events_json":"https://pith.science/api/pith-number/DYRZAM5EAUT2DMZ4QACJNWZDRU/events.json","paper":"https://pith.science/paper/DYRZAM5E"},"agent_actions":{"view_html":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU","download_json":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU.json","view_paper":"https://pith.science/paper/DYRZAM5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19307&json=true","fetch_graph":"https://pith.science/api/pith-number/DYRZAM5EAUT2DMZ4QACJNWZDRU/graph.json","fetch_events":"https://pith.science/api/pith-number/DYRZAM5EAUT2DMZ4QACJNWZDRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/action/storage_attestation","attest_author":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/action/author_attestation","sign_citation":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/action/citation_signature","submit_replication":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/action/replication_record"}},"created_at":"2026-07-05T11:09:27.977571+00:00","updated_at":"2026-07-05T11:09:27.977571+00:00"}