{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQOEAN22RHRSWZ5FK2PXZJZY4Y","short_pith_number":"pith:ZQOEAN22","canonical_record":{"source":{"id":"2403.05973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-09T17:46:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3802f065e4526c3aae7a7a0c5a82c8ef939f4ff529ba536613680913bce9a981","abstract_canon_sha256":"4971061a3eac0df22a9977d3d6a0d4c844f7103e29494562ffe7b024bf4e7798"},"schema_version":"1.0"},"canonical_sha256":"cc1c40375a89e32b67a5569f7ca738e6274645a8d257f71be01a74b846e21c44","source":{"kind":"arxiv","id":"2403.05973","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05973","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05973v1","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05973","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZQOEAN22RHRS","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZQOEAN22RHRSWZ5F","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZQOEAN22","created_at":"2026-07-05T07:54:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQOEAN22RHRSWZ5FK2PXZJZY4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2403.05973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-09T17:46:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3802f065e4526c3aae7a7a0c5a82c8ef939f4ff529ba536613680913bce9a981","abstract_canon_sha256":"4971061a3eac0df22a9977d3d6a0d4c844f7103e29494562ffe7b024bf4e7798"},"schema_version":"1.0"},"canonical_sha256":"cc1c40375a89e32b67a5569f7ca738e6274645a8d257f71be01a74b846e21c44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:16.063413Z","signature_b64":"zBOf3GBuEI+6Y7axUXztABwFwhLlJ1fuhpTLU1n41Bt8EQ/A8dA+V1uP+xhNxXY6y9EDaDDtAXZi9aeTAtL4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1c40375a89e32b67a5569f7ca738e6274645a8d257f71be01a74b846e21c44","last_reissued_at":"2026-07-05T07:54:16.062952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:16.062952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.05973","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DnVFn4UDrCDRMGOWRjgK3vRZ8+IAXDlJUtnQ37HZ66DFKZcoF5+jmbqDSNKkHqeiHq9Q75fC2MPHCAMio1CCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:26:57.027581Z"},"content_sha256":"ff86867a313af0e77a8ee7a6d4c5a5128ba709ab119f9b4bf6d59c5791c306a5","schema_version":"1.0","event_id":"sha256:ff86867a313af0e77a8ee7a6d4c5a5128ba709ab119f9b4bf6d59c5791c306a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQOEAN22RHRSWZ5FK2PXZJZY4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrating Large Language Models Using Their Generations Only","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dennis Ulmer, Hwaran Lee, Martin Gubri, Sangdoo Yun, Seong Joon Oh","submitted_at":"2024-03-09T17:46:24Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model's confidence in its prediction becomes even more important. However, finding effective ways to calibrate LLMs - especially when the only interface to the models is their generated text - remains a challenge. We propose APRICOT (auxiliary prediction of confidence targets): A method to set confidence targets and train an additional model that predicts an LLM's confidence based on its textual input and output alone. This approach has severa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05973","kind":"arxiv","version":1},"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/2403.05973/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":"2026-07-05T07:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MeW4OMYROBy6/A0RjoaMKyLWoSCDK30EKgfP9IQfDbhV36mka6uVm+PgCMy4K62zfRfrD9zD8ObbQQLO9/jgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:26:57.028626Z"},"content_sha256":"c9ae042f746923aca7d14de2432cfd0683daa1affe13afd5ac351c7616ccf35a","schema_version":"1.0","event_id":"sha256:c9ae042f746923aca7d14de2432cfd0683daa1affe13afd5ac351c7616ccf35a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y/bundle.json","state_url":"https://pith.science/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y/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":"2026-08-18T18:26:57Z","links":{"resolver":"https://pith.science/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y","bundle":"https://pith.science/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y/bundle.json","state":"https://pith.science/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQOEAN22RHRSWZ5FK2PXZJZY4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQOEAN22RHRSWZ5FK2PXZJZY4Y","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":"4971061a3eac0df22a9977d3d6a0d4c844f7103e29494562ffe7b024bf4e7798","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-09T17:46:24Z","title_canon_sha256":"3802f065e4526c3aae7a7a0c5a82c8ef939f4ff529ba536613680913bce9a981"},"schema_version":"1.0","source":{"id":"2403.05973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05973","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05973v1","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05973","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZQOEAN22RHRS","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZQOEAN22RHRSWZ5F","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZQOEAN22","created_at":"2026-07-05T07:54:16Z"}],"graph_snapshots":[{"event_id":"sha256:c9ae042f746923aca7d14de2432cfd0683daa1affe13afd5ac351c7616ccf35a","target":"graph","created_at":"2026-07-05T07:54:16Z","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/2403.05973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model's confidence in its prediction becomes even more important. However, finding effective ways to calibrate LLMs - especially when the only interface to the models is their generated text - remains a challenge. We propose APRICOT (auxiliary prediction of confidence targets): A method to set confidence targets and train an additional model that predicts an LLM's confidence based on its textual input and output alone. This approach has severa","authors_text":"Dennis Ulmer, Hwaran Lee, Martin Gubri, Sangdoo Yun, Seong Joon Oh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-09T17:46:24Z","title":"Calibrating Large Language Models Using Their Generations Only"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05973","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:ff86867a313af0e77a8ee7a6d4c5a5128ba709ab119f9b4bf6d59c5791c306a5","target":"record","created_at":"2026-07-05T07:54:16Z","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":"4971061a3eac0df22a9977d3d6a0d4c844f7103e29494562ffe7b024bf4e7798","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-09T17:46:24Z","title_canon_sha256":"3802f065e4526c3aae7a7a0c5a82c8ef939f4ff529ba536613680913bce9a981"},"schema_version":"1.0","source":{"id":"2403.05973","kind":"arxiv","version":1}},"canonical_sha256":"cc1c40375a89e32b67a5569f7ca738e6274645a8d257f71be01a74b846e21c44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc1c40375a89e32b67a5569f7ca738e6274645a8d257f71be01a74b846e21c44","first_computed_at":"2026-07-05T07:54:16.062952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:16.062952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zBOf3GBuEI+6Y7axUXztABwFwhLlJ1fuhpTLU1n41Bt8EQ/A8dA+V1uP+xhNxXY6y9EDaDDtAXZi9aeTAtL4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:16.063413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.05973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff86867a313af0e77a8ee7a6d4c5a5128ba709ab119f9b4bf6d59c5791c306a5","sha256:c9ae042f746923aca7d14de2432cfd0683daa1affe13afd5ac351c7616ccf35a"],"state_sha256":"21f664f37b2282b51e8d93e4ee23c03670f9e0b3925027252d5cdb8791d769a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SgN6rGnTlulKWko4JHN2efTkKCDuA2g3Js55l6Z1V1PVl3BZFpbNcGQhwAgk/5S7Bx0N1qoFPFlb2ajwl9P2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:26:57.035978Z","bundle_sha256":"77b20dc0ef2416baf8f7ec57d4d1a6444132edc875a76ed4cb32f9f3b8231114"}}