{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZIZBTHMJMAMX533TCQFJ4TS4AI","short_pith_number":"pith:ZIZBTHMJ","schema_version":"1.0","canonical_sha256":"ca32199d8960197eef73140a9e4e5c021a8186f598c301114cccc704ac156aee","source":{"kind":"arxiv","id":"2403.17104","version":3},"attestation_state":"computed","paper":{"title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arie Cattan, Aviv Slobodkin, Eran Hirsch, Ido Dagan, Tal Schuster","submitted_at":"2024-03-25T18:41:47Z","abstract_excerpt":"Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. Yet, these citations often point to entire documents or paragraphs, burdening users with extensive verification work. In this paper, we introduce a locally-attributable text generation approach, prioritizing concise attributions. Our method, named \"Attribute First, then Generate\", breaks down the conventional end-to-end generation process into three intuitive"},"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":"2403.17104","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T18:41:47Z","cross_cats_sorted":[],"title_canon_sha256":"2218128edb20ef10d5af9cbddd8305520bfc8f2849f88977295b3f1c60291097","abstract_canon_sha256":"5d888ae6305939f29c73817f8c0fb157e431c070a63cd7fc231dddc647920b1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:15.612198Z","signature_b64":"AEH0gzL5bHdZADG2p9tOUwWBWHSd7+JkvY7tURYluBB8akDlFpCcwYG0GmOwmHLL2QElxBAPDeKQLgBi4EieDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca32199d8960197eef73140a9e4e5c021a8186f598c301114cccc704ac156aee","last_reissued_at":"2026-07-05T08:40:15.611697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:15.611697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arie Cattan, Aviv Slobodkin, Eran Hirsch, Ido Dagan, Tal Schuster","submitted_at":"2024-03-25T18:41:47Z","abstract_excerpt":"Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. Yet, these citations often point to entire documents or paragraphs, burdening users with extensive verification work. In this paper, we introduce a locally-attributable text generation approach, prioritizing concise attributions. Our method, named \"Attribute First, then Generate\", breaks down the conventional end-to-end generation process into three intuitive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17104","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/2403.17104/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":"2403.17104","created_at":"2026-07-05T08:40:15.611762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17104v3","created_at":"2026-07-05T08:40:15.611762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17104","created_at":"2026-07-05T08:40:15.611762+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIZBTHMJMAMX","created_at":"2026-07-05T08:40:15.611762+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIZBTHMJMAMX533T","created_at":"2026-07-05T08:40:15.611762+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIZBTHMJ","created_at":"2026-07-05T08:40:15.611762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":296,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI","json":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI.json","graph_json":"https://pith.science/api/pith-number/ZIZBTHMJMAMX533TCQFJ4TS4AI/graph.json","events_json":"https://pith.science/api/pith-number/ZIZBTHMJMAMX533TCQFJ4TS4AI/events.json","paper":"https://pith.science/paper/ZIZBTHMJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI","download_json":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI.json","view_paper":"https://pith.science/paper/ZIZBTHMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17104&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIZBTHMJMAMX533TCQFJ4TS4AI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIZBTHMJMAMX533TCQFJ4TS4AI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI/action/storage_attestation","attest_author":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI/action/author_attestation","sign_citation":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI/action/citation_signature","submit_replication":"https://pith.science/pith/ZIZBTHMJMAMX533TCQFJ4TS4AI/action/replication_record"}},"created_at":"2026-07-05T08:40:15.611762+00:00","updated_at":"2026-07-05T08:40:15.611762+00:00"}