{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4VYHAM7HC74KYVQF6FCBR2S3SJ","short_pith_number":"pith:4VYHAM7H","schema_version":"1.0","canonical_sha256":"e5707033e717f8ac5605f14418ea5b927affa32329241f3766ecf21d96147e49","source":{"kind":"arxiv","id":"2112.12870","version":2},"attestation_state":"computed","paper":{"title":"Measuring Attribution in Natural Language Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Reitter, Dipanjan Das, Gaurav Singh Tomar, Hannah Rashkin, Iulia Turc, Lora Aroyo, Matthew Lamm, Michael Collins, Slav Petrov, Vitaly Nikolaev","submitted_at":"2021-12-23T22:33:20Z","abstract_excerpt":"With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world. In this work, we present a new evaluation framework entitled Attributable to Identified Sources (AIS) for assessing the output of natural language generation models, when such output pertains to the external world. We first define AIS and introduce a two-stage annotation pipeline for allowing annotators to appropriately evaluate model output according"},"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":"2112.12870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-23T22:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"9f8d53e02cc246af006337f2b236c9295007df7ea9f4d822f81c2e644954d544","abstract_canon_sha256":"aafde440e5536447d1d66b86f82c65728d23fd85fdba40e5a86d22e1bb04965b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:37.458812Z","signature_b64":"m3L1CTE3ecJypncY2K/BMvrUEYh2WN/YMCNVfsI0xzF5GDwktOyb4GBl8G6yAosUAB5NvoGfluyntZ37rZ0SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5707033e717f8ac5605f14418ea5b927affa32329241f3766ecf21d96147e49","last_reissued_at":"2026-07-05T04:45:37.458319Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:37.458319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Attribution in Natural Language Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Reitter, Dipanjan Das, Gaurav Singh Tomar, Hannah Rashkin, Iulia Turc, Lora Aroyo, Matthew Lamm, Michael Collins, Slav Petrov, Vitaly Nikolaev","submitted_at":"2021-12-23T22:33:20Z","abstract_excerpt":"With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world. In this work, we present a new evaluation framework entitled Attributable to Identified Sources (AIS) for assessing the output of natural language generation models, when such output pertains to the external world. We first define AIS and introduce a two-stage annotation pipeline for allowing annotators to appropriately evaluate model output according"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12870","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/2112.12870/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":"2112.12870","created_at":"2026-07-05T04:45:37.458382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12870v2","created_at":"2026-07-05T04:45:37.458382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12870","created_at":"2026-07-05T04:45:37.458382+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VYHAM7HC74K","created_at":"2026-07-05T04:45:37.458382+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VYHAM7HC74KYVQF","created_at":"2026-07-05T04:45:37.458382+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VYHAM7H","created_at":"2026-07-05T04:45:37.458382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25787","citing_title":"How Large Language Models Source Brand Reputation Across Languages and Markets","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11816","citing_title":"WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03728","citing_title":"Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2201.08239","citing_title":"LaMDA: Language Models for Dialog Applications","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2201.11903","citing_title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ","json":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ.json","graph_json":"https://pith.science/api/pith-number/4VYHAM7HC74KYVQF6FCBR2S3SJ/graph.json","events_json":"https://pith.science/api/pith-number/4VYHAM7HC74KYVQF6FCBR2S3SJ/events.json","paper":"https://pith.science/paper/4VYHAM7H"},"agent_actions":{"view_html":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ","download_json":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ.json","view_paper":"https://pith.science/paper/4VYHAM7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12870&json=true","fetch_graph":"https://pith.science/api/pith-number/4VYHAM7HC74KYVQF6FCBR2S3SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4VYHAM7HC74KYVQF6FCBR2S3SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ/action/storage_attestation","attest_author":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ/action/author_attestation","sign_citation":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ/action/citation_signature","submit_replication":"https://pith.science/pith/4VYHAM7HC74KYVQF6FCBR2S3SJ/action/replication_record"}},"created_at":"2026-07-05T04:45:37.458382+00:00","updated_at":"2026-07-05T04:45:37.458382+00:00"}