{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q57JLP7EKBSBYKZKBWP7ANMAM4","short_pith_number":"pith:Q57JLP7E","canonical_record":{"source":{"id":"2402.13213","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T18:24:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a2d422f860b006bddd838cb265bb1717daa887c1c7a67cf74b9ba303ef676275","abstract_canon_sha256":"c01b43d6776eba0485cc1632daedb78e483fb058afa384c775c716956f492e76"},"schema_version":"1.0"},"canonical_sha256":"877e95bfe450641c2b2a0d9ff035806732542746e85ea6e31313bbd36c0dc07c","source":{"kind":"arxiv","id":"2402.13213","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13213","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13213v4","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13213","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q57JLP7EKBSB","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"Q57JLP7EKBSBYKZK","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"Q57JLP7E","created_at":"2026-07-05T11:49:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q57JLP7EKBSBYKZKBWP7ANMAM4","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13213","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T18:24:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a2d422f860b006bddd838cb265bb1717daa887c1c7a67cf74b9ba303ef676275","abstract_canon_sha256":"c01b43d6776eba0485cc1632daedb78e483fb058afa384c775c716956f492e76"},"schema_version":"1.0"},"canonical_sha256":"877e95bfe450641c2b2a0d9ff035806732542746e85ea6e31313bbd36c0dc07c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:45.109285Z","signature_b64":"JL1LtM1kuDI75I28YHj/uk2LPy70mbRwsBHD9LKGilR8ZKFPuinry+Yxi8ZVxeCIo5dLUWwi85RnJnD+NSibCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"877e95bfe450641c2b2a0d9ff035806732542746e85ea6e31313bbd36c0dc07c","last_reissued_at":"2026-07-05T11:49:45.108874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:45.108874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13213","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":"2026-07-05T11:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SIk1SVCTMrM5NsZWD/MZlbWmglp9W82MfhrHWX4N7/GMK+fJP7wtqZTLQ+lNbz2xta/zfEg79hvwnlNDo8uaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:31:58.199398Z"},"content_sha256":"a87a1757553a80eab3ea7b2f30f57f4a64cf41014a915656b02a8b32c6fbea32","schema_version":"1.0","event_id":"sha256:a87a1757553a80eab3ea7b2f30f57f4a64cf41014a915656b02a8b32c6fbea32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q57JLP7EKBSBYKZKBWP7ANMAM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Plaut, Nguyen X. Khanh, Tu Trinh","submitted_at":"2024-02-20T18:24:47Z","abstract_excerpt":"We study 15 large language models (LLMs) fine-tuned for chat and find that their maximum softmax probabilities (MSPs) are consistently miscalibrated on multiple-choice Q&A. However, those MSPs might still encode useful uncertainty information. Specifically, we hypothesized that wrong answers would be associated with smaller MSPs compared to correct answers. Via rigorous statistical testing, we show that this hypothesis holds for models which perform well on the underlying Q&A task. We also find a strong direction correlation between Q&A accuracy and MSP correctness prediction, while finding no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13213","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/2402.13213/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":"2026-07-05T11:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0+JK43VghzgC4e3q9r6Ls771qDUXffJiwgXjB5W3GALUGuRjHuikOCzn44lFDQmY8eJRO2R2srW9kJ/Pm7uAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:31:58.199897Z"},"content_sha256":"74e91bc17631d3058298bfd13a7bafbf78be3637dac55bb15310e67bbaa6684f","schema_version":"1.0","event_id":"sha256:74e91bc17631d3058298bfd13a7bafbf78be3637dac55bb15310e67bbaa6684f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4/bundle.json","state_url":"https://pith.science/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4/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":"2026-08-06T21:31:58Z","links":{"resolver":"https://pith.science/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4","bundle":"https://pith.science/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4/bundle.json","state":"https://pith.science/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q57JLP7EKBSBYKZKBWP7ANMAM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q57JLP7EKBSBYKZKBWP7ANMAM4","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":"c01b43d6776eba0485cc1632daedb78e483fb058afa384c775c716956f492e76","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T18:24:47Z","title_canon_sha256":"a2d422f860b006bddd838cb265bb1717daa887c1c7a67cf74b9ba303ef676275"},"schema_version":"1.0","source":{"id":"2402.13213","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13213","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13213v4","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13213","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q57JLP7EKBSB","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"Q57JLP7EKBSBYKZK","created_at":"2026-07-05T11:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"Q57JLP7E","created_at":"2026-07-05T11:49:45Z"}],"graph_snapshots":[{"event_id":"sha256:74e91bc17631d3058298bfd13a7bafbf78be3637dac55bb15310e67bbaa6684f","target":"graph","created_at":"2026-07-05T11:49:45Z","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/2402.13213/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study 15 large language models (LLMs) fine-tuned for chat and find that their maximum softmax probabilities (MSPs) are consistently miscalibrated on multiple-choice Q&A. However, those MSPs might still encode useful uncertainty information. Specifically, we hypothesized that wrong answers would be associated with smaller MSPs compared to correct answers. Via rigorous statistical testing, we show that this hypothesis holds for models which perform well on the underlying Q&A task. We also find a strong direction correlation between Q&A accuracy and MSP correctness prediction, while finding no","authors_text":"Benjamin Plaut, Nguyen X. Khanh, Tu Trinh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T18:24:47Z","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13213","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:a87a1757553a80eab3ea7b2f30f57f4a64cf41014a915656b02a8b32c6fbea32","target":"record","created_at":"2026-07-05T11:49:45Z","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":"c01b43d6776eba0485cc1632daedb78e483fb058afa384c775c716956f492e76","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T18:24:47Z","title_canon_sha256":"a2d422f860b006bddd838cb265bb1717daa887c1c7a67cf74b9ba303ef676275"},"schema_version":"1.0","source":{"id":"2402.13213","kind":"arxiv","version":4}},"canonical_sha256":"877e95bfe450641c2b2a0d9ff035806732542746e85ea6e31313bbd36c0dc07c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"877e95bfe450641c2b2a0d9ff035806732542746e85ea6e31313bbd36c0dc07c","first_computed_at":"2026-07-05T11:49:45.108874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:45.108874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JL1LtM1kuDI75I28YHj/uk2LPy70mbRwsBHD9LKGilR8ZKFPuinry+Yxi8ZVxeCIo5dLUWwi85RnJnD+NSibCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:45.109285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13213","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a87a1757553a80eab3ea7b2f30f57f4a64cf41014a915656b02a8b32c6fbea32","sha256:74e91bc17631d3058298bfd13a7bafbf78be3637dac55bb15310e67bbaa6684f"],"state_sha256":"fc34bb66f35c85643fffc32d39ef78c80dfdc7e2622a55e12ae30ddaea857e2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rsrwbwuJxEogLxZS9ba7tqCiH/KjwtUTSKEwQ7lsPBfxLuIl5Dba6msf0zCqaqUNk1KhAN03t3mJ4mpRKSerAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:31:58.203144Z","bundle_sha256":"3283bda520e45314f79f0dc7980b189b22109c00be48bf87675b59a8ad7db3b9"}}