{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TN4E2ZGU4QQSUTMJAHSX5ZTLUH","short_pith_number":"pith:TN4E2ZGU","schema_version":"1.0","canonical_sha256":"9b784d64d4e4212a4d8901e57ee66ba1c425f5ed96d5ebfb0f2c15b9e6a7fd95","source":{"kind":"arxiv","id":"2208.09257","version":1},"attestation_state":"computed","paper":{"title":"Ultron: An Ultimate Retriever on Corpus with a Model-based Indexer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jing Yao, Ji-Rong Wen, Ledell Wu, Peitian Zhang, Yujia Zhou, Zhicheng Dou","submitted_at":"2022-08-19T10:28:36Z","abstract_excerpt":"Document retrieval has been extensively studied within the index-retrieve framework for decades, which has withstood the test of time. Unfortunately, such a pipelined framework limits the optimization of the final retrieval quality, because indexing and retrieving are separated stages that can not be jointly optimized in an end-to-end manner. In order to unify these two stages, we explore a model-based indexer for document retrieval. Concretely, we propose Ultron, which encodes the knowledge of all documents into the model and aims to directly retrieve relevant documents end-to-end. For the mo"},"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":"2208.09257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-08-19T10:28:36Z","cross_cats_sorted":[],"title_canon_sha256":"91dfe807ab2511898f9268f4e841206e7bb490e438c365777fe552708658630b","abstract_canon_sha256":"7fb92ad29334ce9cf7147be4f2e295b9ddacdd373c7e68ace565e748cf98d229"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:57.899162Z","signature_b64":"T0m48R8ZDCOIKAFymq5y0xuiQ0DsUoXSI/Givu/I1yE0u49LTP3UbjXVxgz7KsHvblf/G7W3Jw3/Zk5nkMftBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b784d64d4e4212a4d8901e57ee66ba1c425f5ed96d5ebfb0f2c15b9e6a7fd95","last_reissued_at":"2026-07-05T04:49:57.898665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:57.898665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ultron: An Ultimate Retriever on Corpus with a Model-based Indexer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jing Yao, Ji-Rong Wen, Ledell Wu, Peitian Zhang, Yujia Zhou, Zhicheng Dou","submitted_at":"2022-08-19T10:28:36Z","abstract_excerpt":"Document retrieval has been extensively studied within the index-retrieve framework for decades, which has withstood the test of time. Unfortunately, such a pipelined framework limits the optimization of the final retrieval quality, because indexing and retrieving are separated stages that can not be jointly optimized in an end-to-end manner. In order to unify these two stages, we explore a model-based indexer for document retrieval. Concretely, we propose Ultron, which encodes the knowledge of all documents into the model and aims to directly retrieve relevant documents end-to-end. For the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09257","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/2208.09257/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":"2208.09257","created_at":"2026-07-05T04:49:57.898727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.09257v1","created_at":"2026-07-05T04:49:57.898727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09257","created_at":"2026-07-05T04:49:57.898727+00:00"},{"alias_kind":"pith_short_12","alias_value":"TN4E2ZGU4QQS","created_at":"2026-07-05T04:49:57.898727+00:00"},{"alias_kind":"pith_short_16","alias_value":"TN4E2ZGU4QQSUTMJ","created_at":"2026-07-05T04:49:57.898727+00:00"},{"alias_kind":"pith_short_8","alias_value":"TN4E2ZGU","created_at":"2026-07-05T04:49:57.898727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17721","citing_title":"Understanding and Debugging Failures in N-Gram-Based Generative Retrieval","ref_index":47,"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":64,"is_internal_anchor":false},{"citing_arxiv_id":"2411.05572","citing_title":"Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22358","citing_title":"Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23978","citing_title":"Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02773","citing_title":"Model Editing for New Document Integration in Generative Information Retrieval","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23388","citing_title":"A Parametric Memory Head for Continual Generative Retrieval","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23396","citing_title":"Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH","json":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH.json","graph_json":"https://pith.science/api/pith-number/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/graph.json","events_json":"https://pith.science/api/pith-number/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/events.json","paper":"https://pith.science/paper/TN4E2ZGU"},"agent_actions":{"view_html":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH","download_json":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH.json","view_paper":"https://pith.science/paper/TN4E2ZGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.09257&json=true","fetch_graph":"https://pith.science/api/pith-number/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/graph.json","fetch_events":"https://pith.science/api/pith-number/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/action/storage_attestation","attest_author":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/action/author_attestation","sign_citation":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/action/citation_signature","submit_replication":"https://pith.science/pith/TN4E2ZGU4QQSUTMJAHSX5ZTLUH/action/replication_record"}},"created_at":"2026-07-05T04:49:57.898727+00:00","updated_at":"2026-07-05T04:49:57.898727+00:00"}