{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TKM6AVGVWEAJ2VU2QWQ5YOHDID","short_pith_number":"pith:TKM6AVGV","canonical_record":{"source":{"id":"2406.15627","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:06:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26653d7001acef91b8e181d98895d04cf5b540102eb5d0590e39930d8ed8bb29","abstract_canon_sha256":"d440b514fcf68b3aa0dea048554278585fa3a1ce8bca244f5ed5bc0e29067d35"},"schema_version":"1.0"},"canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","source":{"kind":"arxiv","id":"2406.15627","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15627","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15627v4","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15627","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"TKM6AVGVWEAJ","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"TKM6AVGVWEAJ2VU2","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"TKM6AVGV","created_at":"2026-07-05T11:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TKM6AVGVWEAJ2VU2QWQ5YOHDID","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15627","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:06:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26653d7001acef91b8e181d98895d04cf5b540102eb5d0590e39930d8ed8bb29","abstract_canon_sha256":"d440b514fcf68b3aa0dea048554278585fa3a1ce8bca244f5ed5bc0e29067d35"},"schema_version":"1.0"},"canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:59.894812Z","signature_b64":"1HxfV250sYWO/UrzO6U0xwRnOcgTM6AthbEWEe2jWPYXkkABLKsw1Svg/QFjUTvU9yADgrjtRpZxuevq1J95BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","last_reissued_at":"2026-07-05T11:28:59.894276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:59.894276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15627","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t6TpHAIlwyafkbxvS5iX8uC4kque6D5r4gyCiAEbd1qJInYez9AH3YVCRDir9po3OOmYHpVAalZYdsW5w7gBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:48:59.498951Z"},"content_sha256":"f44bfd4544c25910cd2cee89d7598ec37db04d4b268d63699ddff7bbc44b7d4b","schema_version":"1.0","event_id":"sha256:f44bfd4544c25910cd2cee89d7598ec37db04d4b268d63699ddff7bbc44b7d4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TKM6AVGVWEAJ2VU2QWQ5YOHDID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Boda Sadallah, Akim Tsvigun, Alexander Panchenko, Artem Shelmanov, Artem Vazhentsev, Daniil Vasilev, Ekaterina Fadeeva, Kirill Grishchenkov, Lyudmila Rvanova, Maxim Panov, Preslav Nakov, Roman Vashurin, Rui Xing, Sergey Petrakov, Timothy Baldwin","submitted_at":"2024-06-21T20:06:31Z","abstract_excerpt":"The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15627","kind":"arxiv","version":4},"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/2406.15627/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"09nNJHorw6KutLrRaSi08/SZ4kPSOSZguF2JJU27qV5ItRguvY2HTR5Xi/+XLKfdZGhX9RLd4LbjFPYqaKLEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:48:59.499858Z"},"content_sha256":"a261f391263711da06a4d0a5965b79e05aceb4eadc26a94b7999b40735dad78b","schema_version":"1.0","event_id":"sha256:a261f391263711da06a4d0a5965b79e05aceb4eadc26a94b7999b40735dad78b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/bundle.json","state_url":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T04:48:59Z","links":{"resolver":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID","bundle":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/bundle.json","state":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TKM6AVGVWEAJ2VU2QWQ5YOHDID","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":"d440b514fcf68b3aa0dea048554278585fa3a1ce8bca244f5ed5bc0e29067d35","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:06:31Z","title_canon_sha256":"26653d7001acef91b8e181d98895d04cf5b540102eb5d0590e39930d8ed8bb29"},"schema_version":"1.0","source":{"id":"2406.15627","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15627","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15627v4","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15627","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"TKM6AVGVWEAJ","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"TKM6AVGVWEAJ2VU2","created_at":"2026-07-05T11:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"TKM6AVGV","created_at":"2026-07-05T11:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:a261f391263711da06a4d0a5965b79e05aceb4eadc26a94b7999b40735dad78b","target":"graph","created_at":"2026-07-05T11:28:59Z","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/2406.15627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent","authors_text":"Abdelrahman Boda Sadallah, Akim Tsvigun, Alexander Panchenko, Artem Shelmanov, Artem Vazhentsev, Daniil Vasilev, Ekaterina Fadeeva, Kirill Grishchenkov, Lyudmila Rvanova, Maxim Panov, Preslav Nakov, Roman Vashurin, Rui Xing, Sergey Petrakov, Timothy Baldwin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:06:31Z","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15627","kind":"arxiv","version":4},"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:f44bfd4544c25910cd2cee89d7598ec37db04d4b268d63699ddff7bbc44b7d4b","target":"record","created_at":"2026-07-05T11:28:59Z","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":"d440b514fcf68b3aa0dea048554278585fa3a1ce8bca244f5ed5bc0e29067d35","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:06:31Z","title_canon_sha256":"26653d7001acef91b8e181d98895d04cf5b540102eb5d0590e39930d8ed8bb29"},"schema_version":"1.0","source":{"id":"2406.15627","kind":"arxiv","version":4}},"canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","first_computed_at":"2026-07-05T11:28:59.894276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:59.894276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1HxfV250sYWO/UrzO6U0xwRnOcgTM6AthbEWEe2jWPYXkkABLKsw1Svg/QFjUTvU9yADgrjtRpZxuevq1J95BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:59.894812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15627","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f44bfd4544c25910cd2cee89d7598ec37db04d4b268d63699ddff7bbc44b7d4b","sha256:a261f391263711da06a4d0a5965b79e05aceb4eadc26a94b7999b40735dad78b"],"state_sha256":"9e02c9882c1ab77f71a069849f0a00cfe1d38380cd7cc8253607943eb143cbf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"esdA0VjESK8NGpunCcE7JKrzamMjPsTvBP9+de+IbW52yzf9bi7Co4Ou5vbt+c7gEDEibebDBfI6WULtGpxgCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:48:59.538669Z","bundle_sha256":"c7cb6a9719f3874d5017ec9ed39473657d607d5fa7f101e3bb6683066467bf66"}}