{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T7KL6SWSSYIX67GELQS6N6NPGF","short_pith_number":"pith:T7KL6SWS","canonical_record":{"source":{"id":"2501.00555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T17:33:12Z","cross_cats_sorted":["cs.AI","stat.AP","stat.ML"],"title_canon_sha256":"22c307aa3c2a850fcc37ace6a144b035541d5c3a80ba826cb4d022ab5ce580a5","abstract_canon_sha256":"b5d8fcd14bc7641b66dfd21abdc587988a12c6ddc35702462c6c554c40d1a484"},"schema_version":"1.0"},"canonical_sha256":"9fd4bf4ad296117f7cc45c25e6f9af3160599f6c5e908cc8f23f4be2e82805cc","source":{"kind":"arxiv","id":"2501.00555","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00555","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00555v2","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00555","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"T7KL6SWSSYIX","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"T7KL6SWSSYIX67GE","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"T7KL6SWS","created_at":"2026-07-05T11:35:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T7KL6SWSSYIX67GELQS6N6NPGF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T17:33:12Z","cross_cats_sorted":["cs.AI","stat.AP","stat.ML"],"title_canon_sha256":"22c307aa3c2a850fcc37ace6a144b035541d5c3a80ba826cb4d022ab5ce580a5","abstract_canon_sha256":"b5d8fcd14bc7641b66dfd21abdc587988a12c6ddc35702462c6c554c40d1a484"},"schema_version":"1.0"},"canonical_sha256":"9fd4bf4ad296117f7cc45c25e6f9af3160599f6c5e908cc8f23f4be2e82805cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:52.780783Z","signature_b64":"gpOtL/Kd4st0azMouJQXWoQCmh5io5nfrmOhNJptnEyc2L+tQg/gIkhPICKhaHH54Ha8rRtcPnpxEaBTmzJ6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fd4bf4ad296117f7cc45c25e6f9af3160599f6c5e908cc8f23f4be2e82805cc","last_reissued_at":"2026-07-05T11:35:52.780310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:52.780310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00555","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":"2026-07-05T11:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wj/uo1iDT+ItID4DPnHLbXl/rGrXXwrBMl7+noYYaOg94E2BCS67hG2bHT6em1vquHLkWIJgIzUC3lmjBTgpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:31:22.014038Z"},"content_sha256":"ddab2b9ef0594901f112ab6f3fed5b9dce1c3ac09aa06856e9b875af588c5f93","schema_version":"1.0","event_id":"sha256:ddab2b9ef0594901f112ab6f3fed5b9dce1c3ac09aa06856e9b875af588c5f93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T7KL6SWSSYIX67GELQS6N6NPGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Mishler, Harit Vishwakarma, Natraj Raman, Niccol\\`o Dalmasso, Sumitra Ganesh, Thomas Cook","submitted_at":"2024-12-31T17:33:12Z","abstract_excerpt":"Large language models (LLMs) are empowering decision-making in several applications, including tool or API usage and answering multiple-choice questions (MCQs). However, incorrect outputs pose significant risks in high-stakes domains like healthcare and finance. To quantify LLM uncertainty and thereby mitigate these risks, recent works employ conformal prediction (CP), a model- and distribution-agnostic framework that uses LLM outputs to generate a \\emph{prediction set} containing the true answer with high probability. Leveraging CP, we propose \\emph{conformal revision of questions} (CROQ), wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00555","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/2501.00555/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":"2026-07-05T11:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9gbwHg3/BHkOJaCOliJfataxq6dxPGvBkJ1Efeu0it3tNpViUJEd/WHeMXfzHb+yx0WMJJ1PDT/dNX+laUdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:31:22.014444Z"},"content_sha256":"4ca47fc2254f0c9a320ca37357c5114720ae5ce5afb6e9340a4cdf701b902021","schema_version":"1.0","event_id":"sha256:4ca47fc2254f0c9a320ca37357c5114720ae5ce5afb6e9340a4cdf701b902021"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7KL6SWSSYIX67GELQS6N6NPGF/bundle.json","state_url":"https://pith.science/pith/T7KL6SWSSYIX67GELQS6N6NPGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7KL6SWSSYIX67GELQS6N6NPGF/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":"2026-07-09T06:31:22Z","links":{"resolver":"https://pith.science/pith/T7KL6SWSSYIX67GELQS6N6NPGF","bundle":"https://pith.science/pith/T7KL6SWSSYIX67GELQS6N6NPGF/bundle.json","state":"https://pith.science/pith/T7KL6SWSSYIX67GELQS6N6NPGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7KL6SWSSYIX67GELQS6N6NPGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T7KL6SWSSYIX67GELQS6N6NPGF","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":"b5d8fcd14bc7641b66dfd21abdc587988a12c6ddc35702462c6c554c40d1a484","cross_cats_sorted":["cs.AI","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T17:33:12Z","title_canon_sha256":"22c307aa3c2a850fcc37ace6a144b035541d5c3a80ba826cb4d022ab5ce580a5"},"schema_version":"1.0","source":{"id":"2501.00555","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00555","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00555v2","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00555","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"T7KL6SWSSYIX","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"T7KL6SWSSYIX67GE","created_at":"2026-07-05T11:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"T7KL6SWS","created_at":"2026-07-05T11:35:52Z"}],"graph_snapshots":[{"event_id":"sha256:4ca47fc2254f0c9a320ca37357c5114720ae5ce5afb6e9340a4cdf701b902021","target":"graph","created_at":"2026-07-05T11:35:52Z","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/2501.00555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are empowering decision-making in several applications, including tool or API usage and answering multiple-choice questions (MCQs). However, incorrect outputs pose significant risks in high-stakes domains like healthcare and finance. To quantify LLM uncertainty and thereby mitigate these risks, recent works employ conformal prediction (CP), a model- and distribution-agnostic framework that uses LLM outputs to generate a \\emph{prediction set} containing the true answer with high probability. Leveraging CP, we propose \\emph{conformal revision of questions} (CROQ), wh","authors_text":"Alan Mishler, Harit Vishwakarma, Natraj Raman, Niccol\\`o Dalmasso, Sumitra Ganesh, Thomas Cook","cross_cats":["cs.AI","stat.AP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T17:33:12Z","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00555","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:ddab2b9ef0594901f112ab6f3fed5b9dce1c3ac09aa06856e9b875af588c5f93","target":"record","created_at":"2026-07-05T11:35:52Z","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":"b5d8fcd14bc7641b66dfd21abdc587988a12c6ddc35702462c6c554c40d1a484","cross_cats_sorted":["cs.AI","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T17:33:12Z","title_canon_sha256":"22c307aa3c2a850fcc37ace6a144b035541d5c3a80ba826cb4d022ab5ce580a5"},"schema_version":"1.0","source":{"id":"2501.00555","kind":"arxiv","version":2}},"canonical_sha256":"9fd4bf4ad296117f7cc45c25e6f9af3160599f6c5e908cc8f23f4be2e82805cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fd4bf4ad296117f7cc45c25e6f9af3160599f6c5e908cc8f23f4be2e82805cc","first_computed_at":"2026-07-05T11:35:52.780310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:52.780310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gpOtL/Kd4st0azMouJQXWoQCmh5io5nfrmOhNJptnEyc2L+tQg/gIkhPICKhaHH54Ha8rRtcPnpxEaBTmzJ6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:52.780783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00555","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddab2b9ef0594901f112ab6f3fed5b9dce1c3ac09aa06856e9b875af588c5f93","sha256:4ca47fc2254f0c9a320ca37357c5114720ae5ce5afb6e9340a4cdf701b902021"],"state_sha256":"72634378e81a13bcf2b1c4c5ef607916606dcb31ff4953d5663927915a48d7d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSgI9K0mSsgTo5a4PACMvm4pyyd97vO+PuEca3itvVK9uoKn9JBe1Pn9ncl5HBIuMHN9SLv2SME/0XqyP+6jBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:31:22.017433Z","bundle_sha256":"e987db144ee1e91349b8cb90ad9393624759a501c044d1a02a14633e4b3ee082"}}