{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T4RF4IXUL4MIOQW3I7WD6YN7YZ","short_pith_number":"pith:T4RF4IXU","schema_version":"1.0","canonical_sha256":"9f225e22f45f188742db47ec3f61bfc66c5c05da9066ff579a21227f88b73fa8","source":{"kind":"arxiv","id":"2210.08726","version":3},"attestation_state":"computed","paper":{"title":"RARR: Researching and Revising What Language Models Say, Using Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony Chen, Arun Tejasvi Chaganty, Da-Cheng Juan, Hongrae Lee, Kelvin Guu, Luyu Gao, Ni Lao, Panupong Pasupat, Vincent Y. Zhao, Yicheng Fan, Zhuyun Dai","submitted_at":"2022-10-17T03:44:30Z","abstract_excerpt":"Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are trustworthy or not, because most LMs do not have any built-in mechanism for attribution to external evidence. To enable attribution while still preserving all the powerful advantages of recent generation models, we propose RARR (Retrofit Attribution using Research and Revision), a system that 1) automatically finds attribution for the output of any text gen"},"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":"2210.08726","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-17T03:44:30Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"b77f79b549ed55b4407d63b7b41029eca233bb6983a5dabc68eedf82c1b87fd0","abstract_canon_sha256":"4978913df1bae3a2f444531fa5ed0d4415ce6d0f97c97bfa45a0b546772a715c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:00.778143Z","signature_b64":"oUbgALxjbx01jdhpCwPeRGOdkKFQ5Y4UvWC3BlOEbWIu5bpXJA4ZXya+r0f4rYt7THCXx68b/zxTGMn+M40WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f225e22f45f188742db47ec3f61bfc66c5c05da9066ff579a21227f88b73fa8","last_reissued_at":"2026-07-05T06:16:00.777752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:00.777752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RARR: Researching and Revising What Language Models Say, Using Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony Chen, Arun Tejasvi Chaganty, Da-Cheng Juan, Hongrae Lee, Kelvin Guu, Luyu Gao, Ni Lao, Panupong Pasupat, Vincent Y. Zhao, Yicheng Fan, Zhuyun Dai","submitted_at":"2022-10-17T03:44:30Z","abstract_excerpt":"Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are trustworthy or not, because most LMs do not have any built-in mechanism for attribution to external evidence. To enable attribution while still preserving all the powerful advantages of recent generation models, we propose RARR (Retrofit Attribution using Research and Revision), a system that 1) automatically finds attribution for the output of any text gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08726","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/2210.08726/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":"2210.08726","created_at":"2026-07-05T06:16:00.777810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08726v3","created_at":"2026-07-05T06:16:00.777810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08726","created_at":"2026-07-05T06:16:00.777810+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4RF4IXUL4MI","created_at":"2026-07-05T06:16:00.777810+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4RF4IXUL4MIOQW3","created_at":"2026-07-05T06:16:00.777810+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4RF4IXU","created_at":"2026-07-05T06:16:00.777810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08700","citing_title":"Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01256","citing_title":"AI Assistance for Human Review of Default Judgments","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02443","citing_title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2301.13688","citing_title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11036","citing_title":"Uncertainty-Aware Web-Conditioned Scientific Fact-Checking","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ","json":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ.json","graph_json":"https://pith.science/api/pith-number/T4RF4IXUL4MIOQW3I7WD6YN7YZ/graph.json","events_json":"https://pith.science/api/pith-number/T4RF4IXUL4MIOQW3I7WD6YN7YZ/events.json","paper":"https://pith.science/paper/T4RF4IXU"},"agent_actions":{"view_html":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ","download_json":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ.json","view_paper":"https://pith.science/paper/T4RF4IXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08726&json=true","fetch_graph":"https://pith.science/api/pith-number/T4RF4IXUL4MIOQW3I7WD6YN7YZ/graph.json","fetch_events":"https://pith.science/api/pith-number/T4RF4IXUL4MIOQW3I7WD6YN7YZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ/action/storage_attestation","attest_author":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ/action/author_attestation","sign_citation":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ/action/citation_signature","submit_replication":"https://pith.science/pith/T4RF4IXUL4MIOQW3I7WD6YN7YZ/action/replication_record"}},"created_at":"2026-07-05T06:16:00.777810+00:00","updated_at":"2026-07-05T06:16:00.777810+00:00"}