{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VHDYIHH2D373MACKIAOVW45KO4","short_pith_number":"pith:VHDYIHH2","schema_version":"1.0","canonical_sha256":"a9c7841cfa1effb6004a401d5b73aa770ae44dfb9044428f3f94d46d8e5bef0b","source":{"kind":"arxiv","id":"2504.01403","version":2},"attestation_state":"computed","paper":{"title":"Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Changping Peng, Ching Law, Chunyuan Yuan, Donghao Xie, Fanyi Qu, Jingping Shao, Ming Pang, Xiaoyu He, Xue Jiang, Zhangang Lin, Zheng Fang","submitted_at":"2025-04-02T06:40:09Z","abstract_excerpt":"Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems have started to employ LLMs to generate identifiers for product retrieval. Commonly used identifiers include (1) static/semantic IDs and (2) product term sets. The first approach requires creating a product ID system from scratch, missing out on the world knowledge embedded within LLMs. While the second approach leverages this general knowledge, the significa"},"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":"2504.01403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-02T06:40:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce9cda5f6db0309dcb9fcf077dbeb7673462ffe39d9d42341898b23f45d763ab","abstract_canon_sha256":"885d277959de77dcef1780b9d42522dff60b1cdf91c7123faf39f057ba418a88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:13.019583Z","signature_b64":"cg1HGn4pxjc6FtfAwo2DBrP6xUynCZmheiXnm/kDHOZGIdhOuoLnlay41UL4SO1axo/P4ImLtHT44Bf73YFZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9c7841cfa1effb6004a401d5b73aa770ae44dfb9044428f3f94d46d8e5bef0b","last_reissued_at":"2026-07-05T11:35:13.019082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:13.019082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Changping Peng, Ching Law, Chunyuan Yuan, Donghao Xie, Fanyi Qu, Jingping Shao, Ming Pang, Xiaoyu He, Xue Jiang, Zhangang Lin, Zheng Fang","submitted_at":"2025-04-02T06:40:09Z","abstract_excerpt":"Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems have started to employ LLMs to generate identifiers for product retrieval. Commonly used identifiers include (1) static/semantic IDs and (2) product term sets. The first approach requires creating a product ID system from scratch, missing out on the world knowledge embedded within LLMs. While the second approach leverages this general knowledge, the significa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01403","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/2504.01403/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":"2504.01403","created_at":"2026-07-05T11:35:13.019139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01403v2","created_at":"2026-07-05T11:35:13.019139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01403","created_at":"2026-07-05T11:35:13.019139+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHDYIHH2D373","created_at":"2026-07-05T11:35:13.019139+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHDYIHH2D373MACK","created_at":"2026-07-05T11:35:13.019139+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHDYIHH2","created_at":"2026-07-05T11:35:13.019139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27856","citing_title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4","json":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4.json","graph_json":"https://pith.science/api/pith-number/VHDYIHH2D373MACKIAOVW45KO4/graph.json","events_json":"https://pith.science/api/pith-number/VHDYIHH2D373MACKIAOVW45KO4/events.json","paper":"https://pith.science/paper/VHDYIHH2"},"agent_actions":{"view_html":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4","download_json":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4.json","view_paper":"https://pith.science/paper/VHDYIHH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01403&json=true","fetch_graph":"https://pith.science/api/pith-number/VHDYIHH2D373MACKIAOVW45KO4/graph.json","fetch_events":"https://pith.science/api/pith-number/VHDYIHH2D373MACKIAOVW45KO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4/action/storage_attestation","attest_author":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4/action/author_attestation","sign_citation":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4/action/citation_signature","submit_replication":"https://pith.science/pith/VHDYIHH2D373MACKIAOVW45KO4/action/replication_record"}},"created_at":"2026-07-05T11:35:13.019139+00:00","updated_at":"2026-07-05T11:35:13.019139+00:00"}