{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U4QCKXJFQT35IAFVW7WD5YPL4V","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":"1a58a733dfaa265bc43b7d3626992a5b278a7891f84d9bb5a2e5bfafb354d933","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-30T22:30:48Z","title_canon_sha256":"3a974f9733f834e69ce501fa086dba22ab160324921bc1d9992ec51fbcf46fc8"},"schema_version":"1.0","source":{"id":"2507.23135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23135","created_at":"2026-07-05T11:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23135v1","created_at":"2026-07-05T11:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23135","created_at":"2026-07-05T11:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"U4QCKXJFQT35","created_at":"2026-07-05T11:46:06Z"},{"alias_kind":"pith_short_16","alias_value":"U4QCKXJFQT35IAFV","created_at":"2026-07-05T11:46:06Z"},{"alias_kind":"pith_short_8","alias_value":"U4QCKXJF","created_at":"2026-07-05T11:46:06Z"}],"graph_snapshots":[{"event_id":"sha256:72e4765647b2641a2015f47b22a97fd8fab7a9c145be4a2ae17f0d0892dee6db","target":"graph","created_at":"2026-07-05T11:46:06Z","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/2507.23135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding causal relationships across modalities is a core challenge for multimodal models operating in real-world environments. We introduce ISO-Bench, a benchmark for evaluating whether models can infer causal dependencies between visual observations and procedural text. Each example presents an image of a task step and a text snippet from a plan, with the goal of deciding whether the visual step occurs before or after the referenced text step. Evaluation results on ten frontier vision-language models show underwhelming performance: the best zero-shot F1 is only 0.57, and chain-of-though","authors_text":"Ananya Sadana, Jiawei Zhou, Yash Kumar Lal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-30T22:30:48Z","title":"ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual-Language Models through Procedural Plans"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23135","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":"sha256:11d26a74ec6c4363a3722571cc7c2044bef1a03bab85be471109f467cd8f9dc7","target":"record","created_at":"2026-07-05T11:46:06Z","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":"1a58a733dfaa265bc43b7d3626992a5b278a7891f84d9bb5a2e5bfafb354d933","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-30T22:30:48Z","title_canon_sha256":"3a974f9733f834e69ce501fa086dba22ab160324921bc1d9992ec51fbcf46fc8"},"schema_version":"1.0","source":{"id":"2507.23135","kind":"arxiv","version":1}},"canonical_sha256":"a720255d2584f7d400b5b7ec3ee1ebe573ea398e0d119150b700a42acb7e3656","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a720255d2584f7d400b5b7ec3ee1ebe573ea398e0d119150b700a42acb7e3656","first_computed_at":"2026-07-05T11:46:06.255053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:06.255053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T4gcNVgQkl36lNW1Vq9V6C4+Qd/58bAWBaHHaM+qbg21p3cTQejzSCvVLFHEJV/xRXXDsOYlXVfhrkFpZOf4DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:06.255605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11d26a74ec6c4363a3722571cc7c2044bef1a03bab85be471109f467cd8f9dc7","sha256:72e4765647b2641a2015f47b22a97fd8fab7a9c145be4a2ae17f0d0892dee6db"],"state_sha256":"adafb59232e2f3d4297e2895232e23012426c593b07b04eddb5795b8b52133b1"}