{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DYRZAM5EAUT2DMZ4QACJNWZDRU","short_pith_number":"pith:DYRZAM5E","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"},"canonical_sha256":"1e239033a40527a1b33c800496db238d10a9c69ee9fb3190fe2c0817417147e6","source":{"kind":"arxiv","id":"2505.19307","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19307","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19307v1","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19307","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"DYRZAM5EAUT2","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"DYRZAM5EAUT2DMZ4","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"DYRZAM5E","created_at":"2026-07-05T11:09:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DYRZAM5EAUT2DMZ4QACJNWZDRU","target":"record","payload":{"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"},"canonical_sha256":"1e239033a40527a1b33c800496db238d10a9c69ee9fb3190fe2c0817417147e6","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"},"source_kind":"arxiv","source_id":"2505.19307","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":"2026-07-05T11:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZtAvhNttTVU83Ef7kbSrpLU0jPhUwnc4O24JR7tbAFA7mT/AGCIkB3bi5RlbcO605JaR2bDrvpa/v+gOaSR1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:06:55.298276Z"},"content_sha256":"c395d37ae6ddc39f0432e455c9c95136e32fbb33ad4267876ca5feb75760d3f4","schema_version":"1.0","event_id":"sha256:c395d37ae6ddc39f0432e455c9c95136e32fbb33ad4267876ca5feb75760d3f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DYRZAM5EAUT2DMZ4QACJNWZDRU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0rKQeDrWb6hIC+zppopCuZ2l9QkM7aBkWNL8Kv93mmgXQNaPwN8gHraJT0TKCRJcUojI5tQtHO3RcBr8w8hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:06:55.298761Z"},"content_sha256":"6525dcabe3ab594446b6fe51ed2c207757017046a982f765d3162f3298089b6f","schema_version":"1.0","event_id":"sha256:6525dcabe3ab594446b6fe51ed2c207757017046a982f765d3162f3298089b6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/bundle.json","state_url":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/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":"2026-08-08T04:06:55Z","links":{"resolver":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU","bundle":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/bundle.json","state":"https://pith.science/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYRZAM5EAUT2DMZ4QACJNWZDRU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DYRZAM5EAUT2DMZ4QACJNWZDRU","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":"84feda14c0f11ba3006466b80f8b53958896161ec402ae63eb7c75cd94fb0739","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T20:34:12Z","title_canon_sha256":"f8c1f7f6b6865be58dab8937773b63371c6c4b7f986908d5b912beb797f1bd6a"},"schema_version":"1.0","source":{"id":"2505.19307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19307","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19307v1","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19307","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"DYRZAM5EAUT2","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"DYRZAM5EAUT2DMZ4","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"DYRZAM5E","created_at":"2026-07-05T11:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:6525dcabe3ab594446b6fe51ed2c207757017046a982f765d3162f3298089b6f","target":"graph","created_at":"2026-07-05T11:09:27Z","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/2505.19307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bruno Martins, Chenyan Xiong, Jo\\~ao Coelho, Jo\\~ao Magalh\\~aes","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T20:34:12Z","title":"Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19307","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:c395d37ae6ddc39f0432e455c9c95136e32fbb33ad4267876ca5feb75760d3f4","target":"record","created_at":"2026-07-05T11:09:27Z","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":"84feda14c0f11ba3006466b80f8b53958896161ec402ae63eb7c75cd94fb0739","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T20:34:12Z","title_canon_sha256":"f8c1f7f6b6865be58dab8937773b63371c6c4b7f986908d5b912beb797f1bd6a"},"schema_version":"1.0","source":{"id":"2505.19307","kind":"arxiv","version":1}},"canonical_sha256":"1e239033a40527a1b33c800496db238d10a9c69ee9fb3190fe2c0817417147e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e239033a40527a1b33c800496db238d10a9c69ee9fb3190fe2c0817417147e6","first_computed_at":"2026-07-05T11:09:27.977507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:27.977507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HDoO6rVPfzOOeax34uqrprn4CHy6tDXGlvavZNAnxe5evto8zugFDieXXxd9SQKbFPxO/rAu3qLavopEFd09CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:27.979025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c395d37ae6ddc39f0432e455c9c95136e32fbb33ad4267876ca5feb75760d3f4","sha256:6525dcabe3ab594446b6fe51ed2c207757017046a982f765d3162f3298089b6f"],"state_sha256":"700f7487cda00075a2d8be1e970be25a6cf1b9f6b6956bebf7310892195ed0de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Von/7/XaywgkHo6QusNrqhVC6IOQtHkvtUpoUG6Yfqvgfkpn4gygmMFr2cVz3x5FbS+h1GPjPnXZ5PID/q1tCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:06:55.302491Z","bundle_sha256":"e09c25fbfc3f8bb7ea0e625eceaede3ef734bd5469354cc23edb8da5d103e88d"}}