{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LKWG74KBJQNSZCEYBUYKPRVGJV","short_pith_number":"pith:LKWG74KB","schema_version":"1.0","canonical_sha256":"5aac6ff1414c1b2c88980d30a7c6a64d6b46289f1d714c96731940ca257d7460","source":{"kind":"arxiv","id":"2404.15675","version":2},"attestation_state":"computed","paper":{"title":"Hi-Gen: Generative Retrieval For Large-Scale Personalized E-commerce Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jian Wang, Jun Xiao, Rong Xiao, Wenji Zhou, Yanjing Wu, Yinfu Feng, Yunan Ye","submitted_at":"2024-04-24T06:05:35Z","abstract_excerpt":"Leveraging generative retrieval (GR) techniques to enhance search systems is an emerging methodology that has shown promising results in recent years. In GR, a text-to-text model maps string queries directly to relevant document identifiers (docIDs), dramatically simplifying the retrieval process. However, when applying most GR models in large-scale E-commerce for personalized item search, we must face two key problems in encoding and decoding. (1) Existing docID generation methods ignore the encoding of efficiency information, which is critical in E-commerce. (2) The positional information is"},"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":"2404.15675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-24T06:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"fba1d72c2bb92b1740e21a58896c0e9e59a3a5e9a303b125b8598369f04a4d06","abstract_canon_sha256":"59d69d98a667291fafcd31813e931712c8bf557a3301d41ace50dd14c97e84b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:52.941714Z","signature_b64":"xlGpfTrG2AHDsAv0IWpDISeZrODGUw0EasIbN5yjR3oUo44fFRufEq4sj7MSWrk5aEZ2+SoDFeR6ZWg+2TDlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aac6ff1414c1b2c88980d30a7c6a64d6b46289f1d714c96731940ca257d7460","last_reissued_at":"2026-07-05T09:03:52.941283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:52.941283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-Gen: Generative Retrieval For Large-Scale Personalized E-commerce Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jian Wang, Jun Xiao, Rong Xiao, Wenji Zhou, Yanjing Wu, Yinfu Feng, Yunan Ye","submitted_at":"2024-04-24T06:05:35Z","abstract_excerpt":"Leveraging generative retrieval (GR) techniques to enhance search systems is an emerging methodology that has shown promising results in recent years. In GR, a text-to-text model maps string queries directly to relevant document identifiers (docIDs), dramatically simplifying the retrieval process. However, when applying most GR models in large-scale E-commerce for personalized item search, we must face two key problems in encoding and decoding. (1) Existing docID generation methods ignore the encoding of efficiency information, which is critical in E-commerce. (2) The positional information is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15675","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/2404.15675/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":"2404.15675","created_at":"2026-07-05T09:03:52.941344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15675v2","created_at":"2026-07-05T09:03:52.941344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15675","created_at":"2026-07-05T09:03:52.941344+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKWG74KBJQNS","created_at":"2026-07-05T09:03:52.941344+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKWG74KBJQNSZCEY","created_at":"2026-07-05T09:03:52.941344+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKWG74KB","created_at":"2026-07-05T09:03:52.941344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07075","citing_title":"Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14434","citing_title":"Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13273","citing_title":"Mitigating Collaborative Semantic ID Staleness in Generative Retrieval","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV","json":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV.json","graph_json":"https://pith.science/api/pith-number/LKWG74KBJQNSZCEYBUYKPRVGJV/graph.json","events_json":"https://pith.science/api/pith-number/LKWG74KBJQNSZCEYBUYKPRVGJV/events.json","paper":"https://pith.science/paper/LKWG74KB"},"agent_actions":{"view_html":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV","download_json":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV.json","view_paper":"https://pith.science/paper/LKWG74KB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15675&json=true","fetch_graph":"https://pith.science/api/pith-number/LKWG74KBJQNSZCEYBUYKPRVGJV/graph.json","fetch_events":"https://pith.science/api/pith-number/LKWG74KBJQNSZCEYBUYKPRVGJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV/action/storage_attestation","attest_author":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV/action/author_attestation","sign_citation":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV/action/citation_signature","submit_replication":"https://pith.science/pith/LKWG74KBJQNSZCEYBUYKPRVGJV/action/replication_record"}},"created_at":"2026-07-05T09:03:52.941344+00:00","updated_at":"2026-07-05T09:03:52.941344+00:00"}