{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ABFGAYRWJ5NXTNWLUSINFY52G","short_pith_number":"pith:7ABFGAYR","schema_version":"1.0","canonical_sha256":"f802530311b27adbcdb65d2486971dd1969b856e3948f34fa980a2f460ea9a3f","source":{"kind":"arxiv","id":"2406.06125","version":1},"attestation_state":"computed","paper":{"title":"Verifiable Generation with Subsentence-Level Fine-Grained Citations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lu Wang, Shuyang Cao","submitted_at":"2024-06-10T09:32:37Z","abstract_excerpt":"Verifiable generation requires large language models (LLMs) to cite source documents supporting their outputs, thereby improve output transparency and trustworthiness. Yet, previous work mainly targets the generation of sentence-level citations, lacking specificity about which parts of a sentence are backed by the cited sources. This work studies verifiable generation with subsentence-level fine-grained citations for more precise location of generated content supported by the cited sources. We first present a dataset, SCiFi, comprising 10K Wikipedia paragraphs with subsentence-level citations."},"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":"2406.06125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T09:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"0b342cd36fa4f2a40c8967b51985eeb696092ce55d2372efe7c072752d8d77f1","abstract_canon_sha256":"0965a53a9918c3109d98685805deaaf230e32079f8a2d127bc554e1f5d0d2183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:38.121380Z","signature_b64":"wXZf4F2uo92bXRxVWuO85IyAPh/Ev+K/yl5SxSBAserX0nZ2N+EIPcfJjE6LxDoaW2Ovnf4UsGzsXRMtOxWuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f802530311b27adbcdb65d2486971dd1969b856e3948f34fa980a2f460ea9a3f","last_reissued_at":"2026-07-05T08:29:38.120971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:38.120971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verifiable Generation with Subsentence-Level Fine-Grained Citations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lu Wang, Shuyang Cao","submitted_at":"2024-06-10T09:32:37Z","abstract_excerpt":"Verifiable generation requires large language models (LLMs) to cite source documents supporting their outputs, thereby improve output transparency and trustworthiness. Yet, previous work mainly targets the generation of sentence-level citations, lacking specificity about which parts of a sentence are backed by the cited sources. This work studies verifiable generation with subsentence-level fine-grained citations for more precise location of generated content supported by the cited sources. We first present a dataset, SCiFi, comprising 10K Wikipedia paragraphs with subsentence-level citations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06125","kind":"arxiv","version":1},"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/2406.06125/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":"2406.06125","created_at":"2026-07-05T08:29:38.121025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06125v1","created_at":"2026-07-05T08:29:38.121025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06125","created_at":"2026-07-05T08:29:38.121025+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ABFGAYRWJ5N","created_at":"2026-07-05T08:29:38.121025+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ABFGAYRWJ5NXTNW","created_at":"2026-07-05T08:29:38.121025+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ABFGAYR","created_at":"2026-07-05T08:29:38.121025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17843","citing_title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G","json":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G.json","graph_json":"https://pith.science/api/pith-number/7ABFGAYRWJ5NXTNWLUSINFY52G/graph.json","events_json":"https://pith.science/api/pith-number/7ABFGAYRWJ5NXTNWLUSINFY52G/events.json","paper":"https://pith.science/paper/7ABFGAYR"},"agent_actions":{"view_html":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G","download_json":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G.json","view_paper":"https://pith.science/paper/7ABFGAYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06125&json=true","fetch_graph":"https://pith.science/api/pith-number/7ABFGAYRWJ5NXTNWLUSINFY52G/graph.json","fetch_events":"https://pith.science/api/pith-number/7ABFGAYRWJ5NXTNWLUSINFY52G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G/action/storage_attestation","attest_author":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G/action/author_attestation","sign_citation":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G/action/citation_signature","submit_replication":"https://pith.science/pith/7ABFGAYRWJ5NXTNWLUSINFY52G/action/replication_record"}},"created_at":"2026-07-05T08:29:38.121025+00:00","updated_at":"2026-07-05T08:29:38.121025+00:00"}