{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VAHMOTCPY66FMW5WUVSTCTD5RL","short_pith_number":"pith:VAHMOTCP","canonical_record":{"source":{"id":"2605.24756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T22:22:00Z","cross_cats_sorted":[],"title_canon_sha256":"2fdce246582151c38a6ac17d97009b593dfa0734e7c91dda9ff3d80a9c733ba7","abstract_canon_sha256":"65626616c33ca14f8b4d6c9bbdc88ae8c024e8eef61d03891061fe532aa71922"},"schema_version":"1.0"},"canonical_sha256":"a80ec74c4fc7bc565bb6a565314c7d8af827cd813e279c776f39f6f4f091d9fc","source":{"kind":"arxiv","id":"2605.24756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24756","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24756v1","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24756","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"VAHMOTCPY66F","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"VAHMOTCPY66FMW5W","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"VAHMOTCP","created_at":"2026-05-26T01:03:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VAHMOTCPY66FMW5WUVSTCTD5RL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T22:22:00Z","cross_cats_sorted":[],"title_canon_sha256":"2fdce246582151c38a6ac17d97009b593dfa0734e7c91dda9ff3d80a9c733ba7","abstract_canon_sha256":"65626616c33ca14f8b4d6c9bbdc88ae8c024e8eef61d03891061fe532aa71922"},"schema_version":"1.0"},"canonical_sha256":"a80ec74c4fc7bc565bb6a565314c7d8af827cd813e279c776f39f6f4f091d9fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:56.616383Z","signature_b64":"VV7pfLwEsHM5z/B4tLMAlAz/nNYm2vO1WLF18sChta9fLKxAYakr0+Yire7pBsCmWiGHajWCqjxdhHpqGW7gCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a80ec74c4fc7bc565bb6a565314c7d8af827cd813e279c776f39f6f4f091d9fc","last_reissued_at":"2026-05-26T01:03:56.615580Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:56.615580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24756","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":"2026-05-26T01:03:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qtt+3Z42vMSspuRaJdQBe1hYTvfVBCEfMP+X7Z6o7ExdF/3wqpw0xie/HBkfIPK0X7W42Yx3YL489jtLSBFeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T20:25:53.982989Z"},"content_sha256":"e4d68e4b53ff28a8e764b24f71b290e43d4a3ed9e1f4e4f17e84cd54153486c6","schema_version":"1.0","event_id":"sha256:e4d68e4b53ff28a8e764b24f71b290e43d4a3ed9e1f4e4f17e84cd54153486c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VAHMOTCPY66FMW5WUVSTCTD5RL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proper Scoring Rules for Agentic Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Satwik Pandey, Shashwat Pandey, Suresh Raghu","submitted_at":"2026-05-23T22:22:00Z","abstract_excerpt":"Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE, and scalarized trajectory scores evaluate discrimination, binwise calibration, or collapsed summaries, but do not strictly elicit the full prefix-conditioned success-probability trace $q_t = P^{\\pi}(Y=1 | H_t)$. Building on prequential proper scoring, we introduce the Trajectory Proper Score (TPS), a predictor-agnostic family of strictly proper trajectory-level sco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24756","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/2605.24756/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":"2026-05-26T01:03:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y/Fol4/8NWOZuoCBi7f7lWRWrKOYJXZDfZGJEQspeLYHNqLUdbgvUIsDpEn7qEanoCbXNiSjCuI8Blkr06SVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T20:25:53.983373Z"},"content_sha256":"12fd86df44889a821c155df8dac0df6c01d30cd4f0029cb2cf14d23699795a7e","schema_version":"1.0","event_id":"sha256:12fd86df44889a821c155df8dac0df6c01d30cd4f0029cb2cf14d23699795a7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VAHMOTCPY66FMW5WUVSTCTD5RL/bundle.json","state_url":"https://pith.science/pith/VAHMOTCPY66FMW5WUVSTCTD5RL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VAHMOTCPY66FMW5WUVSTCTD5RL/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":"2026-06-08T20:25:53Z","links":{"resolver":"https://pith.science/pith/VAHMOTCPY66FMW5WUVSTCTD5RL","bundle":"https://pith.science/pith/VAHMOTCPY66FMW5WUVSTCTD5RL/bundle.json","state":"https://pith.science/pith/VAHMOTCPY66FMW5WUVSTCTD5RL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VAHMOTCPY66FMW5WUVSTCTD5RL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VAHMOTCPY66FMW5WUVSTCTD5RL","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":"65626616c33ca14f8b4d6c9bbdc88ae8c024e8eef61d03891061fe532aa71922","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T22:22:00Z","title_canon_sha256":"2fdce246582151c38a6ac17d97009b593dfa0734e7c91dda9ff3d80a9c733ba7"},"schema_version":"1.0","source":{"id":"2605.24756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24756","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24756v1","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24756","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"VAHMOTCPY66F","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"VAHMOTCPY66FMW5W","created_at":"2026-05-26T01:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"VAHMOTCP","created_at":"2026-05-26T01:03:56Z"}],"graph_snapshots":[{"event_id":"sha256:12fd86df44889a821c155df8dac0df6c01d30cd4f0029cb2cf14d23699795a7e","target":"graph","created_at":"2026-05-26T01:03:56Z","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/2605.24756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE, and scalarized trajectory scores evaluate discrimination, binwise calibration, or collapsed summaries, but do not strictly elicit the full prefix-conditioned success-probability trace $q_t = P^{\\pi}(Y=1 | H_t)$. Building on prequential proper scoring, we introduce the Trajectory Proper Score (TPS), a predictor-agnostic family of strictly proper trajectory-level sco","authors_text":"Satwik Pandey, Shashwat Pandey, Suresh Raghu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T22:22:00Z","title":"Proper Scoring Rules for Agentic Uncertainty Quantification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24756","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:e4d68e4b53ff28a8e764b24f71b290e43d4a3ed9e1f4e4f17e84cd54153486c6","target":"record","created_at":"2026-05-26T01:03:56Z","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":"65626616c33ca14f8b4d6c9bbdc88ae8c024e8eef61d03891061fe532aa71922","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T22:22:00Z","title_canon_sha256":"2fdce246582151c38a6ac17d97009b593dfa0734e7c91dda9ff3d80a9c733ba7"},"schema_version":"1.0","source":{"id":"2605.24756","kind":"arxiv","version":1}},"canonical_sha256":"a80ec74c4fc7bc565bb6a565314c7d8af827cd813e279c776f39f6f4f091d9fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a80ec74c4fc7bc565bb6a565314c7d8af827cd813e279c776f39f6f4f091d9fc","first_computed_at":"2026-05-26T01:03:56.615580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:56.615580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VV7pfLwEsHM5z/B4tLMAlAz/nNYm2vO1WLF18sChta9fLKxAYakr0+Yire7pBsCmWiGHajWCqjxdhHpqGW7gCA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:56.616383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4d68e4b53ff28a8e764b24f71b290e43d4a3ed9e1f4e4f17e84cd54153486c6","sha256:12fd86df44889a821c155df8dac0df6c01d30cd4f0029cb2cf14d23699795a7e"],"state_sha256":"99095f3ba0b0c241a23d591defaefde622f97eaa25e3554b6b5f3bf46f0320ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDbroGX1Fv+SzcZJZ8NkujLYLYgbU0bNqJt80dU0I1xM6mfx2tGcfFgVjBRL+x4f6Abb/bXmeUwZAtUpo+uPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T20:25:53.986577Z","bundle_sha256":"4ae149f19bc050e492fa426be977a5d454d3826cbb71bff7b46b824a4be4f2e6"}}