{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3KFMXVZHFYEIH3YIZC76RW3GXH","short_pith_number":"pith:3KFMXVZH","canonical_record":{"source":{"id":"2112.11941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T15:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"4066d0b3d28281d7bba1b2480081b97fc96d883ea4eaf5167624f82bfe7577e8","abstract_canon_sha256":"913c56aa436a34e831d7d60f25b1f06c8ea43cc13e72ab6cb76b74b588bd3b77"},"schema_version":"1.0"},"canonical_sha256":"da8acbd7272e0883ef08c8bfe8db66b9efac7e4f074036916c16f15dda27f22c","source":{"kind":"arxiv","id":"2112.11941","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11941","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11941v3","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11941","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"3KFMXVZHFYEI","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"3KFMXVZHFYEIH3YI","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"3KFMXVZH","created_at":"2026-07-05T05:03:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3KFMXVZHFYEIH3YIZC76RW3GXH","target":"record","payload":{"canonical_record":{"source":{"id":"2112.11941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T15:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"4066d0b3d28281d7bba1b2480081b97fc96d883ea4eaf5167624f82bfe7577e8","abstract_canon_sha256":"913c56aa436a34e831d7d60f25b1f06c8ea43cc13e72ab6cb76b74b588bd3b77"},"schema_version":"1.0"},"canonical_sha256":"da8acbd7272e0883ef08c8bfe8db66b9efac7e4f074036916c16f15dda27f22c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:34.374041Z","signature_b64":"+eJLoS4YdLOYn0ydT/1kVRsAD8uFxfePeLVcwpI2q/H1taBnJgoFmyewEKnt6RGoIwDauFJjzZ40nSB+2cSqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da8acbd7272e0883ef08c8bfe8db66b9efac7e4f074036916c16f15dda27f22c","last_reissued_at":"2026-07-05T05:03:34.373606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:34.373606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.11941","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":"2026-07-05T05:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMm0Vg9mNybUa+17CJgyv0bODVZKrTol10QamA8nHSRi4T4x/6CQNlxUHhBbuPqlfjGCL2VMAEamoyY0DTYsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:22:50.888027Z"},"content_sha256":"f654ad3ecfe19cd94c40e4754ac7adf4ea5702e99d903ff180eb279899b46c91","schema_version":"1.0","event_id":"sha256:f654ad3ecfe19cd94c40e4754ac7adf4ea5702e99d903ff180eb279899b46c91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3KFMXVZHFYEIH3YIZC76RW3GXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Frank Binder, J\\\"org Frohberg","submitted_at":"2021-12-22T15:03:23Z","abstract_excerpt":"We introduce the CRASS (counterfactual reasoning assessment) data set and benchmark utilizing questionized counterfactual conditionals as a novel and powerful tool to evaluate large language models. We present the data set design and benchmark that supports scoring against a crowd-validated human baseline. We test six state-of-the-art models against our benchmark. Our results show that it poses a valid challenge for these models and opens up considerable room for their improvement."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11941","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/2112.11941/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":"2026-07-05T05:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwRvyD8EoCzQO3zxKfNAh9KUKQBWxgCFES5xPvOOOWPtbwvY8R2qov6kAh/vTfbgW9boRT5y+Q1pI/HKR737CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:22:50.888642Z"},"content_sha256":"f4f8ea649be27729812888ebc3a50c39c8812a31a8dea359c0f3039fd4cd9cb7","schema_version":"1.0","event_id":"sha256:f4f8ea649be27729812888ebc3a50c39c8812a31a8dea359c0f3039fd4cd9cb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3KFMXVZHFYEIH3YIZC76RW3GXH/bundle.json","state_url":"https://pith.science/pith/3KFMXVZHFYEIH3YIZC76RW3GXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3KFMXVZHFYEIH3YIZC76RW3GXH/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":"2026-08-15T15:22:50Z","links":{"resolver":"https://pith.science/pith/3KFMXVZHFYEIH3YIZC76RW3GXH","bundle":"https://pith.science/pith/3KFMXVZHFYEIH3YIZC76RW3GXH/bundle.json","state":"https://pith.science/pith/3KFMXVZHFYEIH3YIZC76RW3GXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3KFMXVZHFYEIH3YIZC76RW3GXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3KFMXVZHFYEIH3YIZC76RW3GXH","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":"913c56aa436a34e831d7d60f25b1f06c8ea43cc13e72ab6cb76b74b588bd3b77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T15:03:23Z","title_canon_sha256":"4066d0b3d28281d7bba1b2480081b97fc96d883ea4eaf5167624f82bfe7577e8"},"schema_version":"1.0","source":{"id":"2112.11941","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11941","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11941v3","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11941","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"3KFMXVZHFYEI","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"3KFMXVZHFYEIH3YI","created_at":"2026-07-05T05:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"3KFMXVZH","created_at":"2026-07-05T05:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:f4f8ea649be27729812888ebc3a50c39c8812a31a8dea359c0f3039fd4cd9cb7","target":"graph","created_at":"2026-07-05T05:03:34Z","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/2112.11941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the CRASS (counterfactual reasoning assessment) data set and benchmark utilizing questionized counterfactual conditionals as a novel and powerful tool to evaluate large language models. We present the data set design and benchmark that supports scoring against a crowd-validated human baseline. We test six state-of-the-art models against our benchmark. Our results show that it poses a valid challenge for these models and opens up considerable room for their improvement.","authors_text":"Frank Binder, J\\\"org Frohberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T15:03:23Z","title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11941","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:f654ad3ecfe19cd94c40e4754ac7adf4ea5702e99d903ff180eb279899b46c91","target":"record","created_at":"2026-07-05T05:03:34Z","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":"913c56aa436a34e831d7d60f25b1f06c8ea43cc13e72ab6cb76b74b588bd3b77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T15:03:23Z","title_canon_sha256":"4066d0b3d28281d7bba1b2480081b97fc96d883ea4eaf5167624f82bfe7577e8"},"schema_version":"1.0","source":{"id":"2112.11941","kind":"arxiv","version":3}},"canonical_sha256":"da8acbd7272e0883ef08c8bfe8db66b9efac7e4f074036916c16f15dda27f22c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da8acbd7272e0883ef08c8bfe8db66b9efac7e4f074036916c16f15dda27f22c","first_computed_at":"2026-07-05T05:03:34.373606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:34.373606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+eJLoS4YdLOYn0ydT/1kVRsAD8uFxfePeLVcwpI2q/H1taBnJgoFmyewEKnt6RGoIwDauFJjzZ40nSB+2cSqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:34.374041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.11941","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f654ad3ecfe19cd94c40e4754ac7adf4ea5702e99d903ff180eb279899b46c91","sha256:f4f8ea649be27729812888ebc3a50c39c8812a31a8dea359c0f3039fd4cd9cb7"],"state_sha256":"f2c32e7d510de0d7d7ba04a0618199e7c8efd3cef84974df52dcbb92a14609d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DerzyRkUrkL6jIFFjVEffxaqsI4k8etXIyEqDAiQcIaAI38/Sw1XCh4Rg1vjMW3zQ/bck3UD8LaZqKsY4V36DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:22:50.893109Z","bundle_sha256":"811015cbde9614ab3d6241250ca96bb4a0650c471e9214b5c6ec68fca94f66f5"}}