{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5MUPBLXNW7T7S25FRYP5LTIGQB","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":"6f5283f0ca7a48a8ae3010973e872d7eb47f86343a8c67340dcc2b3fa52a9319","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T18:00:23Z","title_canon_sha256":"6b96ffcf43bf4ed46e9cdb58764e8e9884a3d27d7bca47825b9c61b2357c017b"},"schema_version":"1.0","source":{"id":"2310.15239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15239","created_at":"2026-07-05T07:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15239v1","created_at":"2026-07-05T07:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15239","created_at":"2026-07-05T07:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"5MUPBLXNW7T7","created_at":"2026-07-05T07:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"5MUPBLXNW7T7S25F","created_at":"2026-07-05T07:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"5MUPBLXN","created_at":"2026-07-05T07:04:23Z"}],"graph_snapshots":[{"event_id":"sha256:c3abef22fd1cf990aab3c9b7fce248ec9126d7f5a0c3c11d3a3226fd744e14c3","target":"graph","created_at":"2026-07-05T07:04:23Z","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/2310.15239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent efforts in natural language processing (NLP) commonsense reasoning research have yielded a considerable number of new datasets and benchmarks. However, most of these datasets formulate commonsense reasoning challenges in artificial scenarios that are not reflective of the tasks which real-world NLP systems are designed to solve. In this work, we present CRoW, a manually-curated, multi-task benchmark that evaluates the ability of models to apply commonsense reasoning in the context of six real-world NLP tasks. CRoW is constructed using a multi-stage data collection pipeline that rewrites","authors_text":"Antoine Bosselut, Debjit Paul, Mete Ismayilzada, Mor Geva, Syrielle Montariol","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T18:00:23Z","title":"CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15239","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":"sha256:23b2f0f478ce578d919b954ee847e47df8838bf885545a920dddb9c9755f28d4","target":"record","created_at":"2026-07-05T07:04:23Z","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":"6f5283f0ca7a48a8ae3010973e872d7eb47f86343a8c67340dcc2b3fa52a9319","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T18:00:23Z","title_canon_sha256":"6b96ffcf43bf4ed46e9cdb58764e8e9884a3d27d7bca47825b9c61b2357c017b"},"schema_version":"1.0","source":{"id":"2310.15239","kind":"arxiv","version":1}},"canonical_sha256":"eb28f0aeedb7e7f96ba58e1fd5cd06804edf2b61561a7ac1afb8b7001a4c6e65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb28f0aeedb7e7f96ba58e1fd5cd06804edf2b61561a7ac1afb8b7001a4c6e65","first_computed_at":"2026-07-05T07:04:23.171842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:23.171842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FI2ebfgyHymK/YozpWeHTlyekK8dbrQhb9YVTS0ocFDDiSNcUOxHvp0Xyd8RexYVX7D/PinsvfX21gQ5XnskCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:23.172253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23b2f0f478ce578d919b954ee847e47df8838bf885545a920dddb9c9755f28d4","sha256:c3abef22fd1cf990aab3c9b7fce248ec9126d7f5a0c3c11d3a3226fd744e14c3"],"state_sha256":"517eb3bea0b3262ed65b450ab55bb779278678cf703a2d2dc3a66dba6ff02b82"}