{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5E22LMDZVJSW4SLYKLTOY3CF5J","short_pith_number":"pith:5E22LMDZ","schema_version":"1.0","canonical_sha256":"e935a5b079aa656e497852e6ec6c45ea594d9340011da0dd609c9ef606cd606a","source":{"kind":"arxiv","id":"2510.08048","version":4},"attestation_state":"computed","paper":{"title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Chenhe Dong, Dan Ou, Haihong Tang, Jianhui Yang, Pengkun Jiao, Shaowei Yao, Xiaojiang Zhou, Yiming Jin, Zerui Huang","submitted_at":"2025-10-09T10:34:39Z","abstract_excerpt":"Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of business rules and user queries exposes the inability of existing methods to endow models with robust reas"},"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":"2510.08048","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-10-09T10:34:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"db42973812ecf30f2a208535f37ec2522d5cf3cb63f29c99d6662fdd1ab76cda","abstract_canon_sha256":"a678eac6f08ed8e33bc45f3468bb65e8dbf6d75bb0a4f29131f075b92cc06dbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:11.391548Z","signature_b64":"Dg8v/o+OoO2UxERahbu6gbmMI4LXVofux/OsIznkbPnp6eSUS93Dkj9JzerW1/h5hTHQNwCVs/++fX+V2PvWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e935a5b079aa656e497852e6ec6c45ea594d9340011da0dd609c9ef606cd606a","last_reissued_at":"2026-07-07T02:17:11.390551Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:11.390551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Chenhe Dong, Dan Ou, Haihong Tang, Jianhui Yang, Pengkun Jiao, Shaowei Yao, Xiaojiang Zhou, Yiming Jin, Zerui Huang","submitted_at":"2025-10-09T10:34:39Z","abstract_excerpt":"Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of business rules and user queries exposes the inability of existing methods to endow models with robust reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08048","kind":"arxiv","version":4},"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/2510.08048/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":"2510.08048","created_at":"2026-07-07T02:17:11.390652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08048v4","created_at":"2026-07-07T02:17:11.390652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08048","created_at":"2026-07-07T02:17:11.390652+00:00"},{"alias_kind":"pith_short_12","alias_value":"5E22LMDZVJSW","created_at":"2026-07-07T02:17:11.390652+00:00"},{"alias_kind":"pith_short_16","alias_value":"5E22LMDZVJSW4SLY","created_at":"2026-07-07T02:17:11.390652+00:00"},{"alias_kind":"pith_short_8","alias_value":"5E22LMDZ","created_at":"2026-07-07T02:17:11.390652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2602.23620","citing_title":"Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25683","citing_title":"K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J","json":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J.json","graph_json":"https://pith.science/api/pith-number/5E22LMDZVJSW4SLYKLTOY3CF5J/graph.json","events_json":"https://pith.science/api/pith-number/5E22LMDZVJSW4SLYKLTOY3CF5J/events.json","paper":"https://pith.science/paper/5E22LMDZ"},"agent_actions":{"view_html":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J","download_json":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J.json","view_paper":"https://pith.science/paper/5E22LMDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08048&json=true","fetch_graph":"https://pith.science/api/pith-number/5E22LMDZVJSW4SLYKLTOY3CF5J/graph.json","fetch_events":"https://pith.science/api/pith-number/5E22LMDZVJSW4SLYKLTOY3CF5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J/action/storage_attestation","attest_author":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J/action/author_attestation","sign_citation":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J/action/citation_signature","submit_replication":"https://pith.science/pith/5E22LMDZVJSW4SLYKLTOY3CF5J/action/replication_record"}},"created_at":"2026-07-07T02:17:11.390652+00:00","updated_at":"2026-07-07T02:17:11.390652+00:00"}