{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MT54L7KVMO2KI2OXKMC4E6F5LC","short_pith_number":"pith:MT54L7KV","canonical_record":{"source":{"id":"2310.11689","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T03:34:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5846c72eddb4c28e917ae30f975d029c23d3823a28f96c4248ec1fccaa662624","abstract_canon_sha256":"555c0334906aa0fafba96c42747962bf3432e647c1069e7db0a88b2a8bf3cb29"},"schema_version":"1.0"},"canonical_sha256":"64fbc5fd5563b4a469d75305c278bd58afe87cdc66d238a2f60610a193e716fb","source":{"kind":"arxiv","id":"2310.11689","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11689","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11689v2","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11689","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"MT54L7KVMO2K","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"MT54L7KVMO2KI2OX","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"MT54L7KV","created_at":"2026-07-05T07:11:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MT54L7KVMO2KI2OXKMC4E6F5LC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11689","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T03:34:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5846c72eddb4c28e917ae30f975d029c23d3823a28f96c4248ec1fccaa662624","abstract_canon_sha256":"555c0334906aa0fafba96c42747962bf3432e647c1069e7db0a88b2a8bf3cb29"},"schema_version":"1.0"},"canonical_sha256":"64fbc5fd5563b4a469d75305c278bd58afe87cdc66d238a2f60610a193e716fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:36.969495Z","signature_b64":"hPiLuYStdYdzpDzxqKuZZUBWwhNks6vm/JqgtKuGay3uwdvDhVT2Hpk2jtp+DeZRNF/fvnwBuIAZJa6kdyvdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64fbc5fd5563b4a469d75305c278bd58afe87cdc66d238a2f60610a193e716fb","last_reissued_at":"2026-07-05T07:11:36.968988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:36.968988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11689","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tBX99TfLZgiRz32o3zmmmU23RunE2ajEBHtv4NgKcY6pIaRVWoQ/IjmdOP8fGmsSzNBnPrZoE1OscYqVy9DkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:21:54.462624Z"},"content_sha256":"ed4182d56562e3e534ae3963e7606401cd8a89f3bfbeada3276385089625941a","schema_version":"1.0","event_id":"sha256:ed4182d56562e3e534ae3963e7606401cd8a89f3bfbeada3276385089625941a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MT54L7KVMO2KI2OXKMC4E6F5LC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Somesh Jha, Tomas Pfister","submitted_at":"2023-10-18T03:34:59Z","abstract_excerpt":"Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. Selective prediction is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11689","kind":"arxiv","version":2},"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/2310.11689/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":"2026-07-05T07:11:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wd+IKrBSIVG3Ox3sg3xm2HT4GxzfPLBvdWY8gArJ8PN2BqHLPC7qmE9H67cdji8RP4ZSxNNnziNYvHo+yaSKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:21:54.463180Z"},"content_sha256":"b72c1a59b924897e6ae866a353c226652b795f5d1d1999aa501ce0c8a9ba13bc","schema_version":"1.0","event_id":"sha256:b72c1a59b924897e6ae866a353c226652b795f5d1d1999aa501ce0c8a9ba13bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MT54L7KVMO2KI2OXKMC4E6F5LC/bundle.json","state_url":"https://pith.science/pith/MT54L7KVMO2KI2OXKMC4E6F5LC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MT54L7KVMO2KI2OXKMC4E6F5LC/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":"2026-08-06T06:21:54Z","links":{"resolver":"https://pith.science/pith/MT54L7KVMO2KI2OXKMC4E6F5LC","bundle":"https://pith.science/pith/MT54L7KVMO2KI2OXKMC4E6F5LC/bundle.json","state":"https://pith.science/pith/MT54L7KVMO2KI2OXKMC4E6F5LC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MT54L7KVMO2KI2OXKMC4E6F5LC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MT54L7KVMO2KI2OXKMC4E6F5LC","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":"555c0334906aa0fafba96c42747962bf3432e647c1069e7db0a88b2a8bf3cb29","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T03:34:59Z","title_canon_sha256":"5846c72eddb4c28e917ae30f975d029c23d3823a28f96c4248ec1fccaa662624"},"schema_version":"1.0","source":{"id":"2310.11689","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11689","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11689v2","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11689","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"MT54L7KVMO2K","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"MT54L7KVMO2KI2OX","created_at":"2026-07-05T07:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"MT54L7KV","created_at":"2026-07-05T07:11:36Z"}],"graph_snapshots":[{"event_id":"sha256:b72c1a59b924897e6ae866a353c226652b795f5d1d1999aa501ce0c8a9ba13bc","target":"graph","created_at":"2026-07-05T07:11:36Z","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/2310.11689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. Selective prediction is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the ","authors_text":"Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Somesh Jha, Tomas Pfister","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T03:34:59Z","title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11689","kind":"arxiv","version":2},"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:ed4182d56562e3e534ae3963e7606401cd8a89f3bfbeada3276385089625941a","target":"record","created_at":"2026-07-05T07:11:36Z","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":"555c0334906aa0fafba96c42747962bf3432e647c1069e7db0a88b2a8bf3cb29","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T03:34:59Z","title_canon_sha256":"5846c72eddb4c28e917ae30f975d029c23d3823a28f96c4248ec1fccaa662624"},"schema_version":"1.0","source":{"id":"2310.11689","kind":"arxiv","version":2}},"canonical_sha256":"64fbc5fd5563b4a469d75305c278bd58afe87cdc66d238a2f60610a193e716fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64fbc5fd5563b4a469d75305c278bd58afe87cdc66d238a2f60610a193e716fb","first_computed_at":"2026-07-05T07:11:36.968988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:36.968988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hPiLuYStdYdzpDzxqKuZZUBWwhNks6vm/JqgtKuGay3uwdvDhVT2Hpk2jtp+DeZRNF/fvnwBuIAZJa6kdyvdDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:36.969495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11689","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed4182d56562e3e534ae3963e7606401cd8a89f3bfbeada3276385089625941a","sha256:b72c1a59b924897e6ae866a353c226652b795f5d1d1999aa501ce0c8a9ba13bc"],"state_sha256":"51fab62c337aa797a28bf3ce4a1b336833b93a7484d42bf33214228787f68d9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwVJowGmt1yGqchk7Qtlf5q4Nm39+GKeN1uCpqE5Jpr2MaCt+1jS9JjGc8yPGcN9a2LnVx+eXTW/HAs8/PHVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:21:54.466957Z","bundle_sha256":"6402f096b58392be2ecfdc301ce829df9a1273b53a6896be3de9492c21705e24"}}