{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BYQVJSVCV2KDURL66IZEBL5FQC","short_pith_number":"pith:BYQVJSVC","schema_version":"1.0","canonical_sha256":"0e2154caa2ae943a457ef23240afa58089ed472d778911d2161d350efb1ce50e","source":{"kind":"arxiv","id":"2404.14851","version":4},"attestation_state":"computed","paper":{"title":"From Matching to Generation: A Survey on Generative Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jiajie Jin, Peitian Zhang, Xiaoxi Li, Yujia Zhou, Yutao Zhu, Yuyao Zhang, Zhicheng Dou","submitted_at":"2024-04-23T09:05:37Z","abstract_excerpt":"Information Retrieval (IR) systems are crucial tools for users to access information, which have long been dominated by traditional methods relying on similarity matching. With the advancement of pre-trained language models, generative information retrieval (GenIR) emerges as a novel paradigm, attracting increasing attention. Based on the form of information provided to users, current research in GenIR can be categorized into two aspects: \\textbf{(1) Generative Document Retrieval} (GR) leverages the generative model's parameters for memorizing documents, enabling retrieval by directly generati"},"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":"2404.14851","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-23T09:05:37Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8335538b224cf8d6a6c3a6a4be68b9f7286b1c71072c9c66261d24b8c2324b3d","abstract_canon_sha256":"129aef276484fe1f024a5a54242fd402a82a6be65cce66326d0ec00ae80082da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:19.243730Z","signature_b64":"O6BNE+J3O3EG/hC8PwmKnQKtYsTmhiBHLplZoj8nrvVPllKj5rQ70nUhSaY8vMZrVTDgczmnB5EmOtI8fSakAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e2154caa2ae943a457ef23240afa58089ed472d778911d2161d350efb1ce50e","last_reissued_at":"2026-07-05T10:23:19.243262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:19.243262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Matching to Generation: A Survey on Generative Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jiajie Jin, Peitian Zhang, Xiaoxi Li, Yujia Zhou, Yutao Zhu, Yuyao Zhang, Zhicheng Dou","submitted_at":"2024-04-23T09:05:37Z","abstract_excerpt":"Information Retrieval (IR) systems are crucial tools for users to access information, which have long been dominated by traditional methods relying on similarity matching. With the advancement of pre-trained language models, generative information retrieval (GenIR) emerges as a novel paradigm, attracting increasing attention. Based on the form of information provided to users, current research in GenIR can be categorized into two aspects: \\textbf{(1) Generative Document Retrieval} (GR) leverages the generative model's parameters for memorizing documents, enabling retrieval by directly generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14851","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/2404.14851/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":"2404.14851","created_at":"2026-07-05T10:23:19.243320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14851v4","created_at":"2026-07-05T10:23:19.243320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14851","created_at":"2026-07-05T10:23:19.243320+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYQVJSVCV2KD","created_at":"2026-07-05T10:23:19.243320+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYQVJSVCV2KDURL6","created_at":"2026-07-05T10:23:19.243320+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYQVJSVC","created_at":"2026-07-05T10:23:19.243320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17721","citing_title":"Understanding and Debugging Failures in N-Gram-Based Generative Retrieval","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC","json":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC.json","graph_json":"https://pith.science/api/pith-number/BYQVJSVCV2KDURL66IZEBL5FQC/graph.json","events_json":"https://pith.science/api/pith-number/BYQVJSVCV2KDURL66IZEBL5FQC/events.json","paper":"https://pith.science/paper/BYQVJSVC"},"agent_actions":{"view_html":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC","download_json":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC.json","view_paper":"https://pith.science/paper/BYQVJSVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14851&json=true","fetch_graph":"https://pith.science/api/pith-number/BYQVJSVCV2KDURL66IZEBL5FQC/graph.json","fetch_events":"https://pith.science/api/pith-number/BYQVJSVCV2KDURL66IZEBL5FQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC/action/storage_attestation","attest_author":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC/action/author_attestation","sign_citation":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC/action/citation_signature","submit_replication":"https://pith.science/pith/BYQVJSVCV2KDURL66IZEBL5FQC/action/replication_record"}},"created_at":"2026-07-05T10:23:19.243320+00:00","updated_at":"2026-07-05T10:23:19.243320+00:00"}