{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F5VCCCJFWVFTUSIPBBBLHLKRGS","short_pith_number":"pith:F5VCCCJF","canonical_record":{"source":{"id":"2602.08939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-09T17:36:56Z","cross_cats_sorted":[],"title_canon_sha256":"e6a82b7a1ba4c1d2e413011b67ef3022d36b904d119a6f06235a4fc0b7b8d988","abstract_canon_sha256":"cea50e4118cd0dec5bf9d5166be712001adc7d62bf39dbee5613bb9a12287d98"},"schema_version":"1.0"},"canonical_sha256":"2f6a210925b54b3a490f0842b3ad513483f50d43556766044b7b726b5720f2f3","source":{"kind":"arxiv","id":"2602.08939","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08939","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08939v2","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08939","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"F5VCCCJFWVFT","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"F5VCCCJFWVFTUSIP","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"F5VCCCJF","created_at":"2026-06-19T16:09:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F5VCCCJFWVFTUSIPBBBLHLKRGS","target":"record","payload":{"canonical_record":{"source":{"id":"2602.08939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-09T17:36:56Z","cross_cats_sorted":[],"title_canon_sha256":"e6a82b7a1ba4c1d2e413011b67ef3022d36b904d119a6f06235a4fc0b7b8d988","abstract_canon_sha256":"cea50e4118cd0dec5bf9d5166be712001adc7d62bf39dbee5613bb9a12287d98"},"schema_version":"1.0"},"canonical_sha256":"2f6a210925b54b3a490f0842b3ad513483f50d43556766044b7b726b5720f2f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:54.748432Z","signature_b64":"vcmZDratEj+t4FlXneV5ArJ9IRltHs3RnZITP5nq5mq5CxTic5G/g8YqgmOVfwAUpiEF+kICGVTmyYhTD+QEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f6a210925b54b3a490f0842b3ad513483f50d43556766044b7b726b5720f2f3","last_reissued_at":"2026-06-19T16:09:54.748000Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:54.748000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.08939","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":"2026-06-19T16:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CyONqjN7Lfh2JOzcoYXtmc9nPMO0k7WcmHwDn6PLB4SNfwNtBoDiuRo+O0igtYtF1+V0guCNNEl9D0O2sqVVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:00:38.155213Z"},"content_sha256":"c6295d9eaa408fc48e837b04eeeca8616cd1cbfcb2fa3e8f795b1e6a54406dff","schema_version":"1.0","event_id":"sha256:c6295d9eaa408fc48e837b04eeeca8616cd1cbfcb2fa3e8f795b1e6a54406dff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F5VCCCJFWVFTUSIPBBBLHLKRGS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andy Ouyang, Ankit Rai, Daphne Barretto, Edward Y. Chang, Gia Ancone, Longling Geng, Matthew John Hayes, Matthew Wolfman, Patrick Flanagan, Rachael Cooper, Sameer Vijay, Theodore Wu, Yuqiao Zeng","submitted_at":"2026-02-09T17:36:56Z","abstract_excerpt":"Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined. We introduce CTK, a diagnostic benchmark of 5,147 cases and growing, across 10 domains and all three levels of Pearl's Ladder of Causation. Unlike benchmarks that only score correctness, CTK reveals why a model failed by annotating causal rung, trap type, pressure sensitivity, refusal quality, and Utili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08939","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/2602.08939/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":"2026-06-19T16:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsFa5YABn68K7/meW06HrKrsn+GGB+wczx7YCOve074eAVSO6ynA47wVErHlBqu1rCGlRpWIojjB7GD4TFh4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:00:38.155747Z"},"content_sha256":"5d21f43ae57ea96775c2d31e81d79caf3f21aab0433bd88bba97606a7b4910b9","schema_version":"1.0","event_id":"sha256:5d21f43ae57ea96775c2d31e81d79caf3f21aab0433bd88bba97606a7b4910b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS/bundle.json","state_url":"https://pith.science/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS/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":"2026-06-30T17:00:38Z","links":{"resolver":"https://pith.science/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS","bundle":"https://pith.science/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS/bundle.json","state":"https://pith.science/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5VCCCJFWVFTUSIPBBBLHLKRGS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F5VCCCJFWVFTUSIPBBBLHLKRGS","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":"cea50e4118cd0dec5bf9d5166be712001adc7d62bf39dbee5613bb9a12287d98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-09T17:36:56Z","title_canon_sha256":"e6a82b7a1ba4c1d2e413011b67ef3022d36b904d119a6f06235a4fc0b7b8d988"},"schema_version":"1.0","source":{"id":"2602.08939","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08939","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08939v2","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08939","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"F5VCCCJFWVFT","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"F5VCCCJFWVFTUSIP","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"F5VCCCJF","created_at":"2026-06-19T16:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:5d21f43ae57ea96775c2d31e81d79caf3f21aab0433bd88bba97606a7b4910b9","target":"graph","created_at":"2026-06-19T16:09:54Z","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/2602.08939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined. We introduce CTK, a diagnostic benchmark of 5,147 cases and growing, across 10 domains and all three levels of Pearl's Ladder of Causation. Unlike benchmarks that only score correctness, CTK reveals why a model failed by annotating causal rung, trap type, pressure sensitivity, refusal quality, and Utili","authors_text":"Andy Ouyang, Ankit Rai, Daphne Barretto, Edward Y. Chang, Gia Ancone, Longling Geng, Matthew John Hayes, Matthew Wolfman, Patrick Flanagan, Rachael Cooper, Sameer Vijay, Theodore Wu, Yuqiao Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-09T17:36:56Z","title":"CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08939","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:c6295d9eaa408fc48e837b04eeeca8616cd1cbfcb2fa3e8f795b1e6a54406dff","target":"record","created_at":"2026-06-19T16:09:54Z","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":"cea50e4118cd0dec5bf9d5166be712001adc7d62bf39dbee5613bb9a12287d98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-09T17:36:56Z","title_canon_sha256":"e6a82b7a1ba4c1d2e413011b67ef3022d36b904d119a6f06235a4fc0b7b8d988"},"schema_version":"1.0","source":{"id":"2602.08939","kind":"arxiv","version":2}},"canonical_sha256":"2f6a210925b54b3a490f0842b3ad513483f50d43556766044b7b726b5720f2f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f6a210925b54b3a490f0842b3ad513483f50d43556766044b7b726b5720f2f3","first_computed_at":"2026-06-19T16:09:54.748000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:09:54.748000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vcmZDratEj+t4FlXneV5ArJ9IRltHs3RnZITP5nq5mq5CxTic5G/g8YqgmOVfwAUpiEF+kICGVTmyYhTD+QEAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:09:54.748432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.08939","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6295d9eaa408fc48e837b04eeeca8616cd1cbfcb2fa3e8f795b1e6a54406dff","sha256:5d21f43ae57ea96775c2d31e81d79caf3f21aab0433bd88bba97606a7b4910b9"],"state_sha256":"5de618e715187c301599cc844fcb58cbbc7528b8731612606b1eacca947569fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwgQjYC8ZTPRyzC1udzWfdtx4vuwaCAeDljrZFSVkQtp/lDsCC25irChlGeTHxShs2qenY0AGv7k3HMPvRB0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T17:00:38.158368Z","bundle_sha256":"40c176295efc3a42e6d02123c93020d322ee80d1179765cde128503f94b384a5"}}