{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3OFEEWFUMQEFU5HPX5HDMUK7ID","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":"d81355504c1325ed53662ee3e308d3798ff087b8de794ce119c0207901d29d3a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T06:35:37Z","title_canon_sha256":"8edf9a6021cef7e6c97fa148f2a32c970b047535c307acfd98d2c83a4942439f"},"schema_version":"1.0","source":{"id":"2310.19301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19301","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19301v1","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19301","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"3OFEEWFUMQEF","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"3OFEEWFUMQEFU5HP","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"3OFEEWFU","created_at":"2026-07-05T07:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:8d74b6ca3f55867cda4b0050953a4004786779650759209785c2d55964513998","target":"graph","created_at":"2026-07-05T07:06:49Z","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/2310.19301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the fish is not inside the fishbowl. The case, however, may be different for a vision-language model, whose reasoning could gravitate towards the common scenario that the fish is inside the bowl, despite the visual input. In this paper, we introduce a novel probing dataset named ROME (reasoning beyond commonsense knowledge) to evaluate whether the state-of-the-art pre-trained visio","authors_text":"Eason Lai, Jing Jiang, Kankan Zhou, Kyriakos Mouratidis, Wei Bin Au Yeong","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T06:35:37Z","title":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19301","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":"sha256:44d5844b510fb3ffd7f627c96212617098672b117eaba51134edea6125ad1345","target":"record","created_at":"2026-07-05T07:06:49Z","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":"d81355504c1325ed53662ee3e308d3798ff087b8de794ce119c0207901d29d3a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T06:35:37Z","title_canon_sha256":"8edf9a6021cef7e6c97fa148f2a32c970b047535c307acfd98d2c83a4942439f"},"schema_version":"1.0","source":{"id":"2310.19301","kind":"arxiv","version":1}},"canonical_sha256":"db8a4258b464085a74efbf4e36515f40fe8a00a13530febc7d520abdf7de10cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db8a4258b464085a74efbf4e36515f40fe8a00a13530febc7d520abdf7de10cc","first_computed_at":"2026-07-05T07:06:49.013914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:49.013914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YRwfC37+Tcgfvy2ZYCWoVKYj0s6B2jDRzpw2/5UoxwxIAEHYtF5XJz29YlvBuRMt+1ClqpK0uFMmQ+ba2Dr6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:49.014408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44d5844b510fb3ffd7f627c96212617098672b117eaba51134edea6125ad1345","sha256:8d74b6ca3f55867cda4b0050953a4004786779650759209785c2d55964513998"],"state_sha256":"e917bfa77853e66f4f7a84a503d28144b47446098f462760587423ad62ed6ba8"}