{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4VHNEHBFIRFTZ5367I3NRITKOR","short_pith_number":"pith:4VHNEHBF","schema_version":"1.0","canonical_sha256":"e54ed21c25444b3cf77efa36d8a26a745ba9672af43bfe4e6602462141c9001b","source":{"kind":"arxiv","id":"2305.11161","version":1},"attestation_state":"computed","paper":{"title":"TOME: A Two-stage Approach for Model-based Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"HaiFeng Wang, Hua Wu, Jing Liu, Ji-Rong Wen, Ruiyang Ren, Wayne Xin Zhao","submitted_at":"2023-05-18T17:50:22Z","abstract_excerpt":"Recently, model-based retrieval has emerged as a new paradigm in text retrieval that discards the index in the traditional retrieval model and instead memorizes the candidate corpora using model parameters. This design employs a sequence-to-sequence paradigm to generate document identifiers, which enables the complete capture of the relevance between queries and documents and simplifies the classic indexretrieval-rerank pipeline. Despite its attractive qualities, there remain several major challenges in model-based retrieval, including the discrepancy between pre-training and fine-tuning, and "},"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":"2305.11161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-18T17:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"5dee559df56f30c4447bd2a8fdddc2f5e80134e8e5d30ca643b25a50ed83a13a","abstract_canon_sha256":"93b8f22a982dc2b82ce9a96ab935afa3c97cfa5642bfd94b4a6844beda0b287a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:30.964347Z","signature_b64":"FfuxjlNsg+beNqORXtUf9YNSIafU64bm6u4zwspFnWxjv6qZ4k0Bt0ZtDvGl7Sa7G6uw4cQYAAZd5hv57Q6yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e54ed21c25444b3cf77efa36d8a26a745ba9672af43bfe4e6602462141c9001b","last_reissued_at":"2026-07-05T06:11:30.963851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:30.963851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TOME: A Two-stage Approach for Model-based Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"HaiFeng Wang, Hua Wu, Jing Liu, Ji-Rong Wen, Ruiyang Ren, Wayne Xin Zhao","submitted_at":"2023-05-18T17:50:22Z","abstract_excerpt":"Recently, model-based retrieval has emerged as a new paradigm in text retrieval that discards the index in the traditional retrieval model and instead memorizes the candidate corpora using model parameters. This design employs a sequence-to-sequence paradigm to generate document identifiers, which enables the complete capture of the relevance between queries and documents and simplifies the classic indexretrieval-rerank pipeline. Despite its attractive qualities, there remain several major challenges in model-based retrieval, including the discrepancy between pre-training and fine-tuning, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11161","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/2305.11161/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":"2305.11161","created_at":"2026-07-05T06:11:30.963916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11161v1","created_at":"2026-07-05T06:11:30.963916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11161","created_at":"2026-07-05T06:11:30.963916+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VHNEHBFIRFT","created_at":"2026-07-05T06:11:30.963916+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VHNEHBFIRFTZ536","created_at":"2026-07-05T06:11:30.963916+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VHNEHBF","created_at":"2026-07-05T06:11:30.963916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.23978","citing_title":"Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR","json":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR.json","graph_json":"https://pith.science/api/pith-number/4VHNEHBFIRFTZ5367I3NRITKOR/graph.json","events_json":"https://pith.science/api/pith-number/4VHNEHBFIRFTZ5367I3NRITKOR/events.json","paper":"https://pith.science/paper/4VHNEHBF"},"agent_actions":{"view_html":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR","download_json":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR.json","view_paper":"https://pith.science/paper/4VHNEHBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11161&json=true","fetch_graph":"https://pith.science/api/pith-number/4VHNEHBFIRFTZ5367I3NRITKOR/graph.json","fetch_events":"https://pith.science/api/pith-number/4VHNEHBFIRFTZ5367I3NRITKOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR/action/storage_attestation","attest_author":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR/action/author_attestation","sign_citation":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR/action/citation_signature","submit_replication":"https://pith.science/pith/4VHNEHBFIRFTZ5367I3NRITKOR/action/replication_record"}},"created_at":"2026-07-05T06:11:30.963916+00:00","updated_at":"2026-07-05T06:11:30.963916+00:00"}