{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3SBZPNAMM36BCCSSD4BZSIZDP7","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":"6716c707d39ddd8f7388f77b7bf960cc2da5147ad13221cfc72474942569d7c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:40Z","title_canon_sha256":"b0f41e3d113a9674260f5317f44c1e997990ab90ad2300ad763cad8a60991faf"},"schema_version":"1.0","source":{"id":"2406.11278","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11278","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11278v3","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11278","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"3SBZPNAMM36B","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"3SBZPNAMM36BCCSS","created_at":"2026-07-05T10:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"3SBZPNAM","created_at":"2026-07-05T10:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:2e78685f494755a9db9297072cc516f4ecc677be33ec1498220d38473c986ffd","target":"graph","created_at":"2026-07-05T10:13:26Z","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/2406.11278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize token probabilities to assess uncertainty, aggregating multiple token probabilities into a single UE score using a scoring function. Existing scoring functions for probability-based UE, such as length-normalized scoring and semantic contribution-based weighting, are designed to solve certain aspects of the problem but exhibit limitations, including the inability to handle biased probabilities and complex semantic dep","authors_text":"Anil Ramakrishna, Baturalp Buyukates, Chenyang Tao, Dimitrios Dimitriadis, Duygu Nur Yaldiz, Jieyu Zhao, Salman Avestimehr, Yavuz Faruk Bakman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:40Z","title":"Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11278","kind":"arxiv","version":3},"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":"sha256:72a09ab6eb50c1aefe412b7a62b919fbe528bb54c89f4368da3c19a2e87cd50c","target":"record","created_at":"2026-07-05T10:13:26Z","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":"6716c707d39ddd8f7388f77b7bf960cc2da5147ad13221cfc72474942569d7c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:40Z","title_canon_sha256":"b0f41e3d113a9674260f5317f44c1e997990ab90ad2300ad763cad8a60991faf"},"schema_version":"1.0","source":{"id":"2406.11278","kind":"arxiv","version":3}},"canonical_sha256":"dc8397b40c66fc110a521f039923237ffd2bcde15f137e12c8559350dcb8c83b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc8397b40c66fc110a521f039923237ffd2bcde15f137e12c8559350dcb8c83b","first_computed_at":"2026-07-05T10:13:26.580845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:26.580845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"woY2h3ex6w1C4/IaiDZt+0CBKziLr+dX4rON1eW1svlY2izoUbHPcanJ1WIGD07I8xH4T3FvHC/yTI84UPS5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:26.581355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11278","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a09ab6eb50c1aefe412b7a62b919fbe528bb54c89f4368da3c19a2e87cd50c","sha256:2e78685f494755a9db9297072cc516f4ecc677be33ec1498220d38473c986ffd"],"state_sha256":"68c31cc1c3046d238823a65e3f49377f904a0bc2b73ac1414ce8f61629771e55"}