{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NDWUQGAFHHJVTKEFKQZDO26X3J","short_pith_number":"pith:NDWUQGAF","canonical_record":{"source":{"id":"2506.18183","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-22T21:46:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"654bb680806b6427c4a57e8604b12a7bd280031c3a97565892d078276100b630","abstract_canon_sha256":"b6140fd2a8039fcd79953955518bd89c68fc3b7afbd97735686a66b25a9c122a"},"schema_version":"1.0"},"canonical_sha256":"68ed48180539d359a8855432376bd7da6b1979332e3cf594feeee07493718a16","source":{"kind":"arxiv","id":"2506.18183","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18183","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18183v3","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18183","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"NDWUQGAFHHJV","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"NDWUQGAFHHJVTKEF","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"NDWUQGAF","created_at":"2026-07-05T11:39:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NDWUQGAFHHJVTKEFKQZDO26X3J","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18183","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-22T21:46:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"654bb680806b6427c4a57e8604b12a7bd280031c3a97565892d078276100b630","abstract_canon_sha256":"b6140fd2a8039fcd79953955518bd89c68fc3b7afbd97735686a66b25a9c122a"},"schema_version":"1.0"},"canonical_sha256":"68ed48180539d359a8855432376bd7da6b1979332e3cf594feeee07493718a16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:12.495468Z","signature_b64":"gjTO5yBfTwFKiw0y1BjJBGae4SZbHhdSYxFzBgwwuzOPh014EVGVXoG7m10AB8/khIN+UDIvFEK0wVUdynRLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ed48180539d359a8855432376bd7da6b1979332e3cf594feeee07493718a16","last_reissued_at":"2026-07-05T11:39:12.494946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:12.494946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18183","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqRwxKTvfbzlzJHKMD4kbO36LFQG8B8YtWOxW1xAtffYSvgNgyBtpci186q9FjUHv/LVSrLXHwY7cysFKdTWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:32:10.806369Z"},"content_sha256":"d793baac29d9670eefcba9645185fa9ee163e059b16634fc4a94276989c4de52","schema_version":"1.0","event_id":"sha256:d793baac29d9670eefcba9645185fa9ee163e059b16634fc4a94276989c4de52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NDWUQGAFHHJVTKEFKQZDO26X3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anirudha Majumdar, Christina Zhang, Justin Lidard, Ola Shorinwa, Tenny Yin, Zhiting Mei","submitted_at":"2025-06-22T21:46:42Z","abstract_excerpt":"Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks, enabled by multi-step reasoning induced using reinforcement learning. However, like previous language models, reasoning models are prone to generating confident, plausible responses that are incorrect (hallucinations). Knowing when and how much to trust these models is critical to the safe deployment of reasoning models in real-world applications. To this end, we explore uncertainty quantification of reasoning models in this work. Specifically, we ask three fundamental questions: First, are reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18183","kind":"arxiv","version":3},"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/2506.18183/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":"2026-07-05T11:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wCtDexJC+LnKPXZUOttkwt7Nv/M5QrztqkejuXCYbGpDNKZvT/SABEFKJn/JWaFDFmDzcVVEtC/Yo6hKAhqSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:32:10.806750Z"},"content_sha256":"47cf9f2a343847f852830f8a4a51bf82c1ee96fa7fd23e55d313776046782934","schema_version":"1.0","event_id":"sha256:47cf9f2a343847f852830f8a4a51bf82c1ee96fa7fd23e55d313776046782934"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDWUQGAFHHJVTKEFKQZDO26X3J/bundle.json","state_url":"https://pith.science/pith/NDWUQGAFHHJVTKEFKQZDO26X3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDWUQGAFHHJVTKEFKQZDO26X3J/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":"2026-08-04T06:32:10Z","links":{"resolver":"https://pith.science/pith/NDWUQGAFHHJVTKEFKQZDO26X3J","bundle":"https://pith.science/pith/NDWUQGAFHHJVTKEFKQZDO26X3J/bundle.json","state":"https://pith.science/pith/NDWUQGAFHHJVTKEFKQZDO26X3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDWUQGAFHHJVTKEFKQZDO26X3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NDWUQGAFHHJVTKEFKQZDO26X3J","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":"b6140fd2a8039fcd79953955518bd89c68fc3b7afbd97735686a66b25a9c122a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-22T21:46:42Z","title_canon_sha256":"654bb680806b6427c4a57e8604b12a7bd280031c3a97565892d078276100b630"},"schema_version":"1.0","source":{"id":"2506.18183","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18183","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18183v3","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18183","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"NDWUQGAFHHJV","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"NDWUQGAFHHJVTKEF","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"NDWUQGAF","created_at":"2026-07-05T11:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:47cf9f2a343847f852830f8a4a51bf82c1ee96fa7fd23e55d313776046782934","target":"graph","created_at":"2026-07-05T11:39:12Z","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/2506.18183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks, enabled by multi-step reasoning induced using reinforcement learning. However, like previous language models, reasoning models are prone to generating confident, plausible responses that are incorrect (hallucinations). Knowing when and how much to trust these models is critical to the safe deployment of reasoning models in real-world applications. To this end, we explore uncertainty quantification of reasoning models in this work. Specifically, we ask three fundamental questions: First, are reaso","authors_text":"Anirudha Majumdar, Christina Zhang, Justin Lidard, Ola Shorinwa, Tenny Yin, Zhiting Mei","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-22T21:46:42Z","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18183","kind":"arxiv","version":3},"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:d793baac29d9670eefcba9645185fa9ee163e059b16634fc4a94276989c4de52","target":"record","created_at":"2026-07-05T11:39:12Z","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":"b6140fd2a8039fcd79953955518bd89c68fc3b7afbd97735686a66b25a9c122a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-22T21:46:42Z","title_canon_sha256":"654bb680806b6427c4a57e8604b12a7bd280031c3a97565892d078276100b630"},"schema_version":"1.0","source":{"id":"2506.18183","kind":"arxiv","version":3}},"canonical_sha256":"68ed48180539d359a8855432376bd7da6b1979332e3cf594feeee07493718a16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68ed48180539d359a8855432376bd7da6b1979332e3cf594feeee07493718a16","first_computed_at":"2026-07-05T11:39:12.494946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:12.494946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gjTO5yBfTwFKiw0y1BjJBGae4SZbHhdSYxFzBgwwuzOPh014EVGVXoG7m10AB8/khIN+UDIvFEK0wVUdynRLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:12.495468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18183","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d793baac29d9670eefcba9645185fa9ee163e059b16634fc4a94276989c4de52","sha256:47cf9f2a343847f852830f8a4a51bf82c1ee96fa7fd23e55d313776046782934"],"state_sha256":"46bc443d405bc5d59470cf91298216f7ebeb33ec59030cc9d49aea65721533b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c3usLdLCgCXIEq8QmLyMpPNKwaSGNugecrOg6RsTg0LJyiC3WLcasd5/SUgSBCW+qMaBFaRSC/HSYMUkwBkZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:32:10.809980Z","bundle_sha256":"d02985d0e27a704fff8a2fb0712a253c19a601621e5a3c41d0ddb81bb44ba803"}}