{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T4TMJULTW4U3N25Y4HDWGU42GL","short_pith_number":"pith:T4TMJULT","schema_version":"1.0","canonical_sha256":"9f26c4d173b729b6ebb8e1c763539a32c2a006d998bbbd432d04612c32551fce","source":{"kind":"arxiv","id":"2311.08593","version":2},"attestation_state":"computed","paper":{"title":"Summarization-Based Document IDs for Generative Retrieval with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Daniel Cheng, Haoxin Li, Jungo Kasai, Noah A. Smith, Phillip Keung","submitted_at":"2023-11-14T23:28:36Z","abstract_excerpt":"Generative retrieval (Wang et al., 2022; Tay et al., 2022) is a popular approach for end-to-end document retrieval that directly generates document identifiers given an input query. We introduce summarization-based document IDs, in which each document's ID is composed of an extractive summary or abstractive keyphrases generated by a language model, rather than an integer ID sequence or bags of n-grams as proposed in past work. We find that abstractive, content-based IDs (ACID) and an ID based on the first 30 tokens are very effective in direct comparisons with previous approaches to ID creatio"},"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":"2311.08593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T23:28:36Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d419ceedddab0a4b03631e74a502c111c06d5dcea6add5f910a92627ce3fd60a","abstract_canon_sha256":"4189d9b7de179f7f2116f83a9b87ec8c64d3ff6c55810b73540473f5ad928475"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:09.915819Z","signature_b64":"kT1h064DreJ75+xYwuQMRFV00o8nH+n2+X/y4Q7tHKBeLtJWHIFNP7S1PnBXcZXE7IHnqBks9ajJT0BVU41pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f26c4d173b729b6ebb8e1c763539a32c2a006d998bbbd432d04612c32551fce","last_reissued_at":"2026-07-05T09:28:09.915298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:09.915298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Summarization-Based Document IDs for Generative Retrieval with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Daniel Cheng, Haoxin Li, Jungo Kasai, Noah A. Smith, Phillip Keung","submitted_at":"2023-11-14T23:28:36Z","abstract_excerpt":"Generative retrieval (Wang et al., 2022; Tay et al., 2022) is a popular approach for end-to-end document retrieval that directly generates document identifiers given an input query. We introduce summarization-based document IDs, in which each document's ID is composed of an extractive summary or abstractive keyphrases generated by a language model, rather than an integer ID sequence or bags of n-grams as proposed in past work. We find that abstractive, content-based IDs (ACID) and an ID based on the first 30 tokens are very effective in direct comparisons with previous approaches to ID creatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08593","kind":"arxiv","version":2},"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/2311.08593/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":"2311.08593","created_at":"2026-07-05T09:28:09.915365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08593v2","created_at":"2026-07-05T09:28:09.915365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08593","created_at":"2026-07-05T09:28:09.915365+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4TMJULTW4U3","created_at":"2026-07-05T09:28:09.915365+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4TMJULTW4U3N25Y","created_at":"2026-07-05T09:28:09.915365+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4TMJULT","created_at":"2026-07-05T09:28:09.915365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL","json":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL.json","graph_json":"https://pith.science/api/pith-number/T4TMJULTW4U3N25Y4HDWGU42GL/graph.json","events_json":"https://pith.science/api/pith-number/T4TMJULTW4U3N25Y4HDWGU42GL/events.json","paper":"https://pith.science/paper/T4TMJULT"},"agent_actions":{"view_html":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL","download_json":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL.json","view_paper":"https://pith.science/paper/T4TMJULT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08593&json=true","fetch_graph":"https://pith.science/api/pith-number/T4TMJULTW4U3N25Y4HDWGU42GL/graph.json","fetch_events":"https://pith.science/api/pith-number/T4TMJULTW4U3N25Y4HDWGU42GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL/action/storage_attestation","attest_author":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL/action/author_attestation","sign_citation":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL/action/citation_signature","submit_replication":"https://pith.science/pith/T4TMJULTW4U3N25Y4HDWGU42GL/action/replication_record"}},"created_at":"2026-07-05T09:28:09.915365+00:00","updated_at":"2026-07-05T09:28:09.915365+00:00"}