{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3SBZPNAMM36BCCSSD4BZSIZDP7","short_pith_number":"pith:3SBZPNAM","schema_version":"1.0","canonical_sha256":"dc8397b40c66fc110a521f039923237ffd2bcde15f137e12c8559350dcb8c83b","source":{"kind":"arxiv","id":"2406.11278","version":3},"attestation_state":"computed","paper":{"title":"Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anil Ramakrishna, Baturalp Buyukates, Chenyang Tao, Dimitrios Dimitriadis, Duygu Nur Yaldiz, Jieyu Zhao, Salman Avestimehr, Yavuz Faruk Bakman","submitted_at":"2024-06-17T07:30:40Z","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"},"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":"2406.11278","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"b0f41e3d113a9674260f5317f44c1e997990ab90ad2300ad763cad8a60991faf","abstract_canon_sha256":"6716c707d39ddd8f7388f77b7bf960cc2da5147ad13221cfc72474942569d7c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:26.581355Z","signature_b64":"woY2h3ex6w1C4/IaiDZt+0CBKziLr+dX4rON1eW1svlY2izoUbHPcanJ1WIGD07I8xH4T3FvHC/yTI84UPS5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc8397b40c66fc110a521f039923237ffd2bcde15f137e12c8559350dcb8c83b","last_reissued_at":"2026-07-05T10:13:26.580845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:26.580845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anil Ramakrishna, Baturalp Buyukates, Chenyang Tao, Dimitrios Dimitriadis, Duygu Nur Yaldiz, Jieyu Zhao, Salman Avestimehr, Yavuz Faruk Bakman","submitted_at":"2024-06-17T07:30:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11278","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/2406.11278/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":"2406.11278","created_at":"2026-07-05T10:13:26.580904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11278v3","created_at":"2026-07-05T10:13:26.580904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11278","created_at":"2026-07-05T10:13:26.580904+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SBZPNAMM36B","created_at":"2026-07-05T10:13:26.580904+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SBZPNAMM36BCCSS","created_at":"2026-07-05T10:13:26.580904+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SBZPNAM","created_at":"2026-07-05T10:13:26.580904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.15176","citing_title":"Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08974","citing_title":"Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7","json":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7.json","graph_json":"https://pith.science/api/pith-number/3SBZPNAMM36BCCSSD4BZSIZDP7/graph.json","events_json":"https://pith.science/api/pith-number/3SBZPNAMM36BCCSSD4BZSIZDP7/events.json","paper":"https://pith.science/paper/3SBZPNAM"},"agent_actions":{"view_html":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7","download_json":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7.json","view_paper":"https://pith.science/paper/3SBZPNAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11278&json=true","fetch_graph":"https://pith.science/api/pith-number/3SBZPNAMM36BCCSSD4BZSIZDP7/graph.json","fetch_events":"https://pith.science/api/pith-number/3SBZPNAMM36BCCSSD4BZSIZDP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7/action/storage_attestation","attest_author":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7/action/author_attestation","sign_citation":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7/action/citation_signature","submit_replication":"https://pith.science/pith/3SBZPNAMM36BCCSSD4BZSIZDP7/action/replication_record"}},"created_at":"2026-07-05T10:13:26.580904+00:00","updated_at":"2026-07-05T10:13:26.580904+00:00"}