{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CFBKVCDR7J2YJTZRQQ5DKGXFIU","short_pith_number":"pith:CFBKVCDR","schema_version":"1.0","canonical_sha256":"1142aa8871fa7584cf31843a351ae5451fb6b890505718cacca9e71995a9a2a8","source":{"kind":"arxiv","id":"2206.10128","version":3},"attestation_state":"computed","paper":{"title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Guido Zuccon, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Shengyao Zhuang","submitted_at":"2022-06-21T06:21:23Z","abstract_excerpt":"The Differentiable Search Index (DSI) is an emerging paradigm for information retrieval. Unlike traditional retrieval architectures where index and retrieval are two different and separate components, DSI uses a single transformer model to perform both indexing and retrieval.\n  In this paper, we identify and tackle an important issue of current DSI models: the data distribution mismatch that occurs between the DSI indexing and retrieval processes. Specifically, we argue that, at indexing, current DSI methods learn to build connections between the text of long documents and the identifier of th"},"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":"2206.10128","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-21T06:21:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"51631034b8628722abd465342ef539d898a1626efcde3043e05191dbaad7b706","abstract_canon_sha256":"ba0d5a93496f12526dd0b5da1670cb3980c9751bc9838d13cd238ef25c245c7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:31.429292Z","signature_b64":"B56ceAelK1se+zN+Camh0cjnlyo4FtFKwL2WxKufj62X11lkAd5X67laAI5yzfYJuohYdll32bUx+AGdHTXKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1142aa8871fa7584cf31843a351ae5451fb6b890505718cacca9e71995a9a2a8","last_reissued_at":"2026-07-05T06:28:31.428886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:31.428886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Guido Zuccon, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Shengyao Zhuang","submitted_at":"2022-06-21T06:21:23Z","abstract_excerpt":"The Differentiable Search Index (DSI) is an emerging paradigm for information retrieval. Unlike traditional retrieval architectures where index and retrieval are two different and separate components, DSI uses a single transformer model to perform both indexing and retrieval.\n  In this paper, we identify and tackle an important issue of current DSI models: the data distribution mismatch that occurs between the DSI indexing and retrieval processes. Specifically, we argue that, at indexing, current DSI methods learn to build connections between the text of long documents and the identifier of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10128","kind":"arxiv","version":3},"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/2206.10128/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":"2206.10128","created_at":"2026-07-05T06:28:31.428940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10128v3","created_at":"2026-07-05T06:28:31.428940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10128","created_at":"2026-07-05T06:28:31.428940+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFBKVCDR7J2Y","created_at":"2026-07-05T06:28:31.428940+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFBKVCDR7J2YJTZR","created_at":"2026-07-05T06:28:31.428940+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFBKVCDR","created_at":"2026-07-05T06:28:31.428940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":65,"is_internal_anchor":false},{"citing_arxiv_id":"2411.05572","citing_title":"Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04952","citing_title":"Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU","json":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU.json","graph_json":"https://pith.science/api/pith-number/CFBKVCDR7J2YJTZRQQ5DKGXFIU/graph.json","events_json":"https://pith.science/api/pith-number/CFBKVCDR7J2YJTZRQQ5DKGXFIU/events.json","paper":"https://pith.science/paper/CFBKVCDR"},"agent_actions":{"view_html":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU","download_json":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU.json","view_paper":"https://pith.science/paper/CFBKVCDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10128&json=true","fetch_graph":"https://pith.science/api/pith-number/CFBKVCDR7J2YJTZRQQ5DKGXFIU/graph.json","fetch_events":"https://pith.science/api/pith-number/CFBKVCDR7J2YJTZRQQ5DKGXFIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU/action/storage_attestation","attest_author":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU/action/author_attestation","sign_citation":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU/action/citation_signature","submit_replication":"https://pith.science/pith/CFBKVCDR7J2YJTZRQQ5DKGXFIU/action/replication_record"}},"created_at":"2026-07-05T06:28:31.428940+00:00","updated_at":"2026-07-05T06:28:31.428940+00:00"}