{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PESDJIY7G3YW5WDUAWXCYXRFD5","short_pith_number":"pith:PESDJIY7","canonical_record":{"source":{"id":"2508.05544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T16:22:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c10277c53566176b450959c766db3ec14bfac1826cba32ec1198919b49752a1b","abstract_canon_sha256":"2be366311f5ec0693cf2f2f78e7176006d5e557126e9d3205164b10b87bf4ef0"},"schema_version":"1.0"},"canonical_sha256":"792434a31f36f16ed87405ae2c5e251f4659adb7968fd54ec6cd3dbff1239cfc","source":{"kind":"arxiv","id":"2508.05544","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05544","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05544v1","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05544","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"pith_short_12","alias_value":"PESDJIY7G3YW","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"pith_short_16","alias_value":"PESDJIY7G3YW5WDU","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"pith_short_8","alias_value":"PESDJIY7","created_at":"2026-07-05T11:50:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PESDJIY7G3YW5WDUAWXCYXRFD5","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T16:22:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c10277c53566176b450959c766db3ec14bfac1826cba32ec1198919b49752a1b","abstract_canon_sha256":"2be366311f5ec0693cf2f2f78e7176006d5e557126e9d3205164b10b87bf4ef0"},"schema_version":"1.0"},"canonical_sha256":"792434a31f36f16ed87405ae2c5e251f4659adb7968fd54ec6cd3dbff1239cfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:15.163163Z","signature_b64":"+G7AQZOpzRNLwUZYvuSpyPzt5kggmEZD9kd+jBHRCI94TrY1vggBaY9pxO0yhW0PM2aSZ9msJkmjKsoEkxlKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"792434a31f36f16ed87405ae2c5e251f4659adb7968fd54ec6cd3dbff1239cfc","last_reissued_at":"2026-07-05T11:50:15.162751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:15.162751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05544","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":"2026-07-05T11:50:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAc/j2Qa+dedBJqfPavUbTJfhUFDtnftVyo8xofdQD6ru5dwM9ZYVM7lgoLIFboKjGRWFhqgILS0Mpw6092TDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T06:57:11.821196Z"},"content_sha256":"ba4a151df75f0fc06c301923eeed9828085405ae010a0286bb472fca4cacae8d","schema_version":"1.0","event_id":"sha256:ba4a151df75f0fc06c301923eeed9828085405ae010a0286bb472fca4cacae8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PESDJIY7G3YW5WDUAWXCYXRFD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conformal Sets in Multiple-Choice Question Answering under Black-Box Settings with Provable Coverage Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guang Yang, Xinyang Liu","submitted_at":"2025-08-07T16:22:49Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable progress in multiple-choice question answering (MCQA), but their inherent unreliability, such as hallucination and overconfidence, limits their application in high-risk domains. To address this, we propose a frequency-based uncertainty quantification method under black-box settings, leveraging conformal prediction (CP) to ensure provable coverage guarantees. Our approach involves multiple independent samplings of the model's output distribution for each input, with the most frequent sample serving as a reference to calculate predictive entropy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05544","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/2508.05544/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":"2026-07-05T11:50:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5YoXGgGGhRUQ910a9UiMUqqzwG9yx5oIG4tePcuhcZQyZCZ9yi+1KgkLs1FjFsXAtlzJYm6pluwYF02uV4amCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T06:57:11.821586Z"},"content_sha256":"c10c8c0dcf5e49114f375730e98b41e73fc5c76eebd0c4b52626edef44f97560","schema_version":"1.0","event_id":"sha256:c10c8c0dcf5e49114f375730e98b41e73fc5c76eebd0c4b52626edef44f97560"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PESDJIY7G3YW5WDUAWXCYXRFD5/bundle.json","state_url":"https://pith.science/pith/PESDJIY7G3YW5WDUAWXCYXRFD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PESDJIY7G3YW5WDUAWXCYXRFD5/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":"2026-07-06T06:57:11Z","links":{"resolver":"https://pith.science/pith/PESDJIY7G3YW5WDUAWXCYXRFD5","bundle":"https://pith.science/pith/PESDJIY7G3YW5WDUAWXCYXRFD5/bundle.json","state":"https://pith.science/pith/PESDJIY7G3YW5WDUAWXCYXRFD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PESDJIY7G3YW5WDUAWXCYXRFD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PESDJIY7G3YW5WDUAWXCYXRFD5","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":"2be366311f5ec0693cf2f2f78e7176006d5e557126e9d3205164b10b87bf4ef0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T16:22:49Z","title_canon_sha256":"c10277c53566176b450959c766db3ec14bfac1826cba32ec1198919b49752a1b"},"schema_version":"1.0","source":{"id":"2508.05544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05544","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05544v1","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05544","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"pith_short_12","alias_value":"PESDJIY7G3YW","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"pith_short_16","alias_value":"PESDJIY7G3YW5WDU","created_at":"2026-07-05T11:50:15Z"},{"alias_kind":"pith_short_8","alias_value":"PESDJIY7","created_at":"2026-07-05T11:50:15Z"}],"graph_snapshots":[{"event_id":"sha256:c10c8c0dcf5e49114f375730e98b41e73fc5c76eebd0c4b52626edef44f97560","target":"graph","created_at":"2026-07-05T11:50:15Z","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/2508.05544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable progress in multiple-choice question answering (MCQA), but their inherent unreliability, such as hallucination and overconfidence, limits their application in high-risk domains. To address this, we propose a frequency-based uncertainty quantification method under black-box settings, leveraging conformal prediction (CP) to ensure provable coverage guarantees. Our approach involves multiple independent samplings of the model's output distribution for each input, with the most frequent sample serving as a reference to calculate predictive entropy","authors_text":"Guang Yang, Xinyang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T16:22:49Z","title":"Conformal Sets in Multiple-Choice Question Answering under Black-Box Settings with Provable Coverage Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05544","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:ba4a151df75f0fc06c301923eeed9828085405ae010a0286bb472fca4cacae8d","target":"record","created_at":"2026-07-05T11:50:15Z","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":"2be366311f5ec0693cf2f2f78e7176006d5e557126e9d3205164b10b87bf4ef0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T16:22:49Z","title_canon_sha256":"c10277c53566176b450959c766db3ec14bfac1826cba32ec1198919b49752a1b"},"schema_version":"1.0","source":{"id":"2508.05544","kind":"arxiv","version":1}},"canonical_sha256":"792434a31f36f16ed87405ae2c5e251f4659adb7968fd54ec6cd3dbff1239cfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"792434a31f36f16ed87405ae2c5e251f4659adb7968fd54ec6cd3dbff1239cfc","first_computed_at":"2026-07-05T11:50:15.162751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:15.162751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+G7AQZOpzRNLwUZYvuSpyPzt5kggmEZD9kd+jBHRCI94TrY1vggBaY9pxO0yhW0PM2aSZ9msJkmjKsoEkxlKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:15.163163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba4a151df75f0fc06c301923eeed9828085405ae010a0286bb472fca4cacae8d","sha256:c10c8c0dcf5e49114f375730e98b41e73fc5c76eebd0c4b52626edef44f97560"],"state_sha256":"89936e3032f1664b2e6ecad8265bf73035eef4ea92f9a898ed793eb8045b6262"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rrRrVor81WXG5hF2kg00Vm2gnERycvHBAsvqn/nPcOV993MStjLvYu46G5xovG3BCu0gh9ppZ/8rWrkuIV0TDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T06:57:11.823577Z","bundle_sha256":"d408ca2f3457e83215e56fd9a685cd96ba6d3c2b4a71412df01e3ebd2a5f5c1c"}}