{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJYD64TDXYS4HIE2O3GVPMNUMR","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":"2917e842d5874a681f71419b3392867d2a1909e5f98a3dda504d15f107203639","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T14:50:10Z","title_canon_sha256":"207db90850eb6206aba1934487a44c89c46745e12b1ea01a044e22a1f0d28823"},"schema_version":"1.0","source":{"id":"2404.07060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07060","created_at":"2026-07-05T08:06:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07060v1","created_at":"2026-07-05T08:06:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07060","created_at":"2026-07-05T08:06:34Z"},{"alias_kind":"pith_short_12","alias_value":"NJYD64TDXYS4","created_at":"2026-07-05T08:06:34Z"},{"alias_kind":"pith_short_16","alias_value":"NJYD64TDXYS4HIE2","created_at":"2026-07-05T08:06:34Z"},{"alias_kind":"pith_short_8","alias_value":"NJYD64TD","created_at":"2026-07-05T08:06:34Z"}],"graph_snapshots":[{"event_id":"sha256:41efbaadad1b890af33d82c51fe9751f2a2867f843129bdd620c092d3ddba876","target":"graph","created_at":"2026-07-05T08:06:34Z","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/2404.07060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an empirical study of groundedness in long-form question answering (LFQA) by retrieval-augmented large language models (LLMs). In particular, we evaluate whether every generated sentence is grounded in the retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded, even when those sentences contain correct ground-truth answers. Additionally, we examine the impacts of factors such as model size, decoding strategy, and instruction tuning on groundedness","authors_text":"Alessandro Stolfo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T14:50:10Z","title":"Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07060","kind":"arxiv","version":1},"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":"sha256:647519a8423241d7b4e024a557f6ffd5ec6fa911c4c60da663edc8c1a616cc8d","target":"record","created_at":"2026-07-05T08:06:34Z","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":"2917e842d5874a681f71419b3392867d2a1909e5f98a3dda504d15f107203639","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T14:50:10Z","title_canon_sha256":"207db90850eb6206aba1934487a44c89c46745e12b1ea01a044e22a1f0d28823"},"schema_version":"1.0","source":{"id":"2404.07060","kind":"arxiv","version":1}},"canonical_sha256":"6a703f7263be25c3a09a76cd57b1b46457641b7588b606226b225ba6d031d5a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a703f7263be25c3a09a76cd57b1b46457641b7588b606226b225ba6d031d5a0","first_computed_at":"2026-07-05T08:06:34.565529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:34.565529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wmFLmxkl7V9sX9uEij/beGlD4gQtemwcxJSDcHsPbl1DtzKUISekIW0sC3z6JWWZfO9G6cTzUSiukSNi4OznCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:34.565998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:647519a8423241d7b4e024a557f6ffd5ec6fa911c4c60da663edc8c1a616cc8d","sha256:41efbaadad1b890af33d82c51fe9751f2a2867f843129bdd620c092d3ddba876"],"state_sha256":"99175a5d9c80866da2a0b230f2a1c63132159a8b45fb319cb12706a19c6ed270"}