{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C4WQ2B7Q6BKZBCQJKTRMOH4LAB","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":"b19cd748a58a10735b14739274a80fc45911d4391d4733bce6a927d8e9f81287","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T22:23:27Z","title_canon_sha256":"19904528eb98f7524219f0282edfcb3fe16ad678474a2ab9be7fc976e434dd19"},"schema_version":"1.0","source":{"id":"2311.17076","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17076","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17076v3","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17076","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"C4WQ2B7Q6BKZ","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"C4WQ2B7Q6BKZBCQJ","created_at":"2026-07-05T08:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"C4WQ2B7Q","created_at":"2026-07-05T08:02:48Z"}],"graph_snapshots":[{"event_id":"sha256:28f4a8488f6119f4f4565dd02402e15a4078eef8704ef4bca16c9a8124161049","target":"graph","created_at":"2026-07-05T08:02:48Z","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/2311.17076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The combination of strong visual backbones and Large Language Model (LLM) reasoning has led to Large Multimodal Models (LMMs) becoming the current standard for a wide range of vision and language (VL) tasks. However, recent research has shown that even the most advanced LMMs still struggle to capture aspects of compositional visual reasoning, such as attributes and relationships between objects. One solution is to utilize scene graphs (SGs)--a formalization of objects and their relations and attributes that has been extensively used as a bridge between the visual and textual domains. Yet, scen","authors_text":"Brandon Huang, Chancharik Mitra, Roei Herzig, Trevor Darrell","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T22:23:27Z","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17076","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:a33776276309380804917d02533735911c94919c93661ec371387ff461dc9b3a","target":"record","created_at":"2026-07-05T08:02:48Z","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":"b19cd748a58a10735b14739274a80fc45911d4391d4733bce6a927d8e9f81287","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T22:23:27Z","title_canon_sha256":"19904528eb98f7524219f0282edfcb3fe16ad678474a2ab9be7fc976e434dd19"},"schema_version":"1.0","source":{"id":"2311.17076","kind":"arxiv","version":3}},"canonical_sha256":"172d0d07f0f055908a0954e2c71f8b007e134803e70385bcb9946952fa031c0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"172d0d07f0f055908a0954e2c71f8b007e134803e70385bcb9946952fa031c0d","first_computed_at":"2026-07-05T08:02:48.662331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:48.662331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xeIHP/rFNvh7hVJD9LqgDJwpkgjYZVBCOcLjq2FqwmWFN21N/976NZPrKdj+A4hjluU9E6xmmypVW7Vgg4miAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:48.662830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17076","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a33776276309380804917d02533735911c94919c93661ec371387ff461dc9b3a","sha256:28f4a8488f6119f4f4565dd02402e15a4078eef8704ef4bca16c9a8124161049"],"state_sha256":"0d5b88e64e5c047b296cc55e4c7bb644222d921d85f3558213fdd004393a90c5"}