{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GVNWFVKFMF3GNK3CF2QWKROS32","short_pith_number":"pith:GVNWFVKF","schema_version":"1.0","canonical_sha256":"355b62d545617666ab622ea16545d2de8dd03ba8c522262f17e8862c8bcbbd5a","source":{"kind":"arxiv","id":"2406.01197","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Generative Information Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chao-Wei Huang, Sheng-Yang Wu, Tzu-Lin Kuo, Tzung-Sheng Lin, Tzu-Wei Chiu, Yun-Nung Chen","submitted_at":"2024-06-03T10:59:33Z","abstract_excerpt":"Generative Retrieval (GR) is an emerging paradigm in information retrieval that leverages generative models to directly map queries to relevant document identifiers (DocIDs) without the need for traditional query processing or document reranking. This survey provides a comprehensive overview of GR, highlighting key developments, indexing and retrieval strategies, and challenges. We discuss various document identifier strategies, including numerical and string-based identifiers, and explore different document representation methods. Our primary contribution lies in outlining future research dir"},"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":"2406.01197","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-03T10:59:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"89bfe690e641d525797a528a28722bf039edddd864de1280b71cff4e8578ce6a","abstract_canon_sha256":"19532b67c38326dd9f53b701019b55abfdd9446918b647861cb29d079443fac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:10.756951Z","signature_b64":"iRbaBNQvszKGK3NCrtqL48pW2KhOW7Ae0is82mlYnd1eDQIPuC7lKKcJv5WUgP8WI/0nbOZ4YMYgfu8aJnMQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355b62d545617666ab622ea16545d2de8dd03ba8c522262f17e8862c8bcbbd5a","last_reissued_at":"2026-07-05T08:27:10.756535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:10.756535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Generative Information Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chao-Wei Huang, Sheng-Yang Wu, Tzu-Lin Kuo, Tzung-Sheng Lin, Tzu-Wei Chiu, Yun-Nung Chen","submitted_at":"2024-06-03T10:59:33Z","abstract_excerpt":"Generative Retrieval (GR) is an emerging paradigm in information retrieval that leverages generative models to directly map queries to relevant document identifiers (DocIDs) without the need for traditional query processing or document reranking. This survey provides a comprehensive overview of GR, highlighting key developments, indexing and retrieval strategies, and challenges. We discuss various document identifier strategies, including numerical and string-based identifiers, and explore different document representation methods. Our primary contribution lies in outlining future research dir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01197","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/2406.01197/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":"2406.01197","created_at":"2026-07-05T08:27:10.756594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01197v2","created_at":"2026-07-05T08:27:10.756594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01197","created_at":"2026-07-05T08:27:10.756594+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVNWFVKFMF3G","created_at":"2026-07-05T08:27:10.756594+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVNWFVKFMF3GNK3C","created_at":"2026-07-05T08:27:10.756594+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVNWFVKF","created_at":"2026-07-05T08:27:10.756594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17721","citing_title":"Understanding and Debugging Failures in N-Gram-Based Generative Retrieval","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07075","citing_title":"Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce","ref_index":12,"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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32","json":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32.json","graph_json":"https://pith.science/api/pith-number/GVNWFVKFMF3GNK3CF2QWKROS32/graph.json","events_json":"https://pith.science/api/pith-number/GVNWFVKFMF3GNK3CF2QWKROS32/events.json","paper":"https://pith.science/paper/GVNWFVKF"},"agent_actions":{"view_html":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32","download_json":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32.json","view_paper":"https://pith.science/paper/GVNWFVKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01197&json=true","fetch_graph":"https://pith.science/api/pith-number/GVNWFVKFMF3GNK3CF2QWKROS32/graph.json","fetch_events":"https://pith.science/api/pith-number/GVNWFVKFMF3GNK3CF2QWKROS32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32/action/storage_attestation","attest_author":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32/action/author_attestation","sign_citation":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32/action/citation_signature","submit_replication":"https://pith.science/pith/GVNWFVKFMF3GNK3CF2QWKROS32/action/replication_record"}},"created_at":"2026-07-05T08:27:10.756594+00:00","updated_at":"2026-07-05T08:27:10.756594+00:00"}