{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OFEEWFUMQEFU5HPX5HDMUK7ID","short_pith_number":"pith:3OFEEWFU","schema_version":"1.0","canonical_sha256":"db8a4258b464085a74efbf4e36515f40fe8a00a13530febc7d520abdf7de10cc","source":{"kind":"arxiv","id":"2310.19301","version":1},"attestation_state":"computed","paper":{"title":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Eason Lai, Jing Jiang, Kankan Zhou, Kyriakos Mouratidis, Wei Bin Au Yeong","submitted_at":"2023-10-30T06:35:37Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.19301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T06:35:37Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8edf9a6021cef7e6c97fa148f2a32c970b047535c307acfd98d2c83a4942439f","abstract_canon_sha256":"d81355504c1325ed53662ee3e308d3798ff087b8de794ce119c0207901d29d3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:49.014408Z","signature_b64":"YRwfC37+Tcgfvy2ZYCWoVKYj0s6B2jDRzpw2/5UoxwxIAEHYtF5XJz29YlvBuRMt+1ClqpK0uFMmQ+ba2Dr6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8a4258b464085a74efbf4e36515f40fe8a00a13530febc7d520abdf7de10cc","last_reissued_at":"2026-07-05T07:06:49.013914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:49.013914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Eason Lai, Jing Jiang, Kankan Zhou, Kyriakos Mouratidis, Wei Bin Au Yeong","submitted_at":"2023-10-30T06:35:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19301","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/2310.19301/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.19301","created_at":"2026-07-05T07:06:49.013973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19301v1","created_at":"2026-07-05T07:06:49.013973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19301","created_at":"2026-07-05T07:06:49.013973+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OFEEWFUMQEF","created_at":"2026-07-05T07:06:49.013973+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OFEEWFUMQEFU5HP","created_at":"2026-07-05T07:06:49.013973+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OFEEWFU","created_at":"2026-07-05T07:06:49.013973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID","json":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID.json","graph_json":"https://pith.science/api/pith-number/3OFEEWFUMQEFU5HPX5HDMUK7ID/graph.json","events_json":"https://pith.science/api/pith-number/3OFEEWFUMQEFU5HPX5HDMUK7ID/events.json","paper":"https://pith.science/paper/3OFEEWFU"},"agent_actions":{"view_html":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID","download_json":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID.json","view_paper":"https://pith.science/paper/3OFEEWFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19301&json=true","fetch_graph":"https://pith.science/api/pith-number/3OFEEWFUMQEFU5HPX5HDMUK7ID/graph.json","fetch_events":"https://pith.science/api/pith-number/3OFEEWFUMQEFU5HPX5HDMUK7ID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID/action/storage_attestation","attest_author":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID/action/author_attestation","sign_citation":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID/action/citation_signature","submit_replication":"https://pith.science/pith/3OFEEWFUMQEFU5HPX5HDMUK7ID/action/replication_record"}},"created_at":"2026-07-05T07:06:49.013973+00:00","updated_at":"2026-07-05T07:06:49.013973+00:00"}