{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AMFTSYU7CG65HDMEKZ6HPFZQ6P","short_pith_number":"pith:AMFTSYU7","schema_version":"1.0","canonical_sha256":"030b39629f11bdd38d84567c779730f3ddbe4c156bec0ebadc2caea238a56b43","source":{"kind":"arxiv","id":"2306.11397","version":1},"attestation_state":"computed","paper":{"title":"Generative Retrieval as Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Thong Nguyen","submitted_at":"2023-06-20T09:04:06Z","abstract_excerpt":"Generative retrieval is a promising new neural retrieval paradigm that aims to optimize the retrieval pipeline by performing both indexing and retrieval with a single transformer model. However, this new paradigm faces challenges with updating the index and scaling to large collections. In this paper, we analyze two prominent variants of generative retrieval and show that they can be conceptually viewed as bi-encoders for dense retrieval. Specifically, we analytically demonstrate that the generative retrieval process can be decomposed into dot products between query and document vectors, simil"},"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":"2306.11397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-20T09:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"faffdb5f0a486e2b9b3b2f0b24be5156e82e5d2ec85a2e42496d6c442058a0ff","abstract_canon_sha256":"c770ec50e258670a0b97de38c1ef458ea88fef49d119c777e3fa3c7bec0242ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:19.345988Z","signature_b64":"iBudFzVuqHSiFG5Ai9n2GHj1JplneRxRF0NbzWmDIO0rOGDsRW93mddSle3L1VmAFbnS6vzia4oA1uqoYm8GCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"030b39629f11bdd38d84567c779730f3ddbe4c156bec0ebadc2caea238a56b43","last_reissued_at":"2026-07-05T06:22:19.345555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:19.345555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Retrieval as Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Thong Nguyen","submitted_at":"2023-06-20T09:04:06Z","abstract_excerpt":"Generative retrieval is a promising new neural retrieval paradigm that aims to optimize the retrieval pipeline by performing both indexing and retrieval with a single transformer model. However, this new paradigm faces challenges with updating the index and scaling to large collections. In this paper, we analyze two prominent variants of generative retrieval and show that they can be conceptually viewed as bi-encoders for dense retrieval. Specifically, we analytically demonstrate that the generative retrieval process can be decomposed into dot products between query and document vectors, simil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11397","kind":"arxiv","version":1},"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/2306.11397/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":"2306.11397","created_at":"2026-07-05T06:22:19.345621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11397v1","created_at":"2026-07-05T06:22:19.345621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11397","created_at":"2026-07-05T06:22:19.345621+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMFTSYU7CG65","created_at":"2026-07-05T06:22:19.345621+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMFTSYU7CG65HDME","created_at":"2026-07-05T06:22:19.345621+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMFTSYU7","created_at":"2026-07-05T06:22:19.345621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02842","citing_title":"Foundations of GenIR","ref_index":138,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P","json":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P.json","graph_json":"https://pith.science/api/pith-number/AMFTSYU7CG65HDMEKZ6HPFZQ6P/graph.json","events_json":"https://pith.science/api/pith-number/AMFTSYU7CG65HDMEKZ6HPFZQ6P/events.json","paper":"https://pith.science/paper/AMFTSYU7"},"agent_actions":{"view_html":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P","download_json":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P.json","view_paper":"https://pith.science/paper/AMFTSYU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11397&json=true","fetch_graph":"https://pith.science/api/pith-number/AMFTSYU7CG65HDMEKZ6HPFZQ6P/graph.json","fetch_events":"https://pith.science/api/pith-number/AMFTSYU7CG65HDMEKZ6HPFZQ6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P/action/storage_attestation","attest_author":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P/action/author_attestation","sign_citation":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P/action/citation_signature","submit_replication":"https://pith.science/pith/AMFTSYU7CG65HDMEKZ6HPFZQ6P/action/replication_record"}},"created_at":"2026-07-05T06:22:19.345621+00:00","updated_at":"2026-07-05T06:22:19.345621+00:00"}