{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T4TMJULTW4U3N25Y4HDWGU42GL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4189d9b7de179f7f2116f83a9b87ec8c64d3ff6c55810b73540473f5ad928475","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T23:28:36Z","title_canon_sha256":"d419ceedddab0a4b03631e74a502c111c06d5dcea6add5f910a92627ce3fd60a"},"schema_version":"1.0","source":{"id":"2311.08593","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08593","created_at":"2026-07-05T09:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08593v2","created_at":"2026-07-05T09:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08593","created_at":"2026-07-05T09:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"T4TMJULTW4U3","created_at":"2026-07-05T09:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"T4TMJULTW4U3N25Y","created_at":"2026-07-05T09:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"T4TMJULT","created_at":"2026-07-05T09:28:09Z"}],"graph_snapshots":[{"event_id":"sha256:fca62bac2ea50f9631a11a95eb4e9625e84c64116faaeb4a5b1bea1913b6548d","target":"graph","created_at":"2026-07-05T09:28:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.08593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daniel Cheng, Haoxin Li, Jungo Kasai, Noah A. Smith, Phillip Keung","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T23:28:36Z","title":"Summarization-Based Document IDs for Generative Retrieval with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08593","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac773eea7f32f63cda8ade08c9f5cc8e8e3a2ec4bde97911f483884f10c1ef03","target":"record","created_at":"2026-07-05T09:28:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4189d9b7de179f7f2116f83a9b87ec8c64d3ff6c55810b73540473f5ad928475","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T23:28:36Z","title_canon_sha256":"d419ceedddab0a4b03631e74a502c111c06d5dcea6add5f910a92627ce3fd60a"},"schema_version":"1.0","source":{"id":"2311.08593","kind":"arxiv","version":2}},"canonical_sha256":"9f26c4d173b729b6ebb8e1c763539a32c2a006d998bbbd432d04612c32551fce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f26c4d173b729b6ebb8e1c763539a32c2a006d998bbbd432d04612c32551fce","first_computed_at":"2026-07-05T09:28:09.915298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:09.915298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kT1h064DreJ75+xYwuQMRFV00o8nH+n2+X/y4Q7tHKBeLtJWHIFNP7S1PnBXcZXE7IHnqBks9ajJT0BVU41pBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:09.915819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08593","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac773eea7f32f63cda8ade08c9f5cc8e8e3a2ec4bde97911f483884f10c1ef03","sha256:fca62bac2ea50f9631a11a95eb4e9625e84c64116faaeb4a5b1bea1913b6548d"],"state_sha256":"460cdbf5fbf4217299622485e6ee7c0a916b822e049ec19cd4b3397e80e8867d"}