{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SEZ3OBPR2UC2YMMLDFUXTFGGWG","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":"afe26f32f7091106a295c9b55250a851dd94b3d15584e745ccb0436f291969e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T01:09:21Z","title_canon_sha256":"f831425c87751a439777a12758177ba92b87d78dbc85058a59127de218d6767c"},"schema_version":"1.0","source":{"id":"2411.15201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15201","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15201v1","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15201","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_12","alias_value":"SEZ3OBPR2UC2","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_16","alias_value":"SEZ3OBPR2UC2YMML","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_8","alias_value":"SEZ3OBPR","created_at":"2026-07-05T09:39:31Z"}],"graph_snapshots":[{"event_id":"sha256:b8bf3f5f78e78487bbb6c002ada0dfb92985386a341379947f88b661052cebea","target":"graph","created_at":"2026-07-05T09:39:31Z","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/2411.15201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current benchmarks for evaluating Vision Language Models (VLMs) often fall short in thoroughly assessing model abilities to understand and process complex visual and textual content. They typically focus on simple tasks that do not require deep reasoning or the integration of multiple data modalities to solve an original problem. To address this gap, we introduce the PARROT-360V Benchmark, a novel and comprehensive benchmark featuring 2487 challenging visual puzzles designed to test VLMs on complex visual reasoning tasks. We evaluated leading models: GPT-4o, Claude-3.5-Sonnet, and Gemini-1.5-P","authors_text":"Aviral Srivastava, Basem Rizk, Harsha Vardhan Khurdula, Indus Khaitan, Janit Anjaria, Rajvardhan Khaitan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T01:09:21Z","title":"Beyond Visual Understanding: Introducing PARROT-360V for Vision Language Model Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15201","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:b6a154d7410daa2e40e5d71894f97bf7ddb42d7b884580e23d9457b876cef366","target":"record","created_at":"2026-07-05T09:39:31Z","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":"afe26f32f7091106a295c9b55250a851dd94b3d15584e745ccb0436f291969e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T01:09:21Z","title_canon_sha256":"f831425c87751a439777a12758177ba92b87d78dbc85058a59127de218d6767c"},"schema_version":"1.0","source":{"id":"2411.15201","kind":"arxiv","version":1}},"canonical_sha256":"9133b705f1d505ac318b19697994c6b1b09a69e94ff2504dc270f9937228ba9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9133b705f1d505ac318b19697994c6b1b09a69e94ff2504dc270f9937228ba9a","first_computed_at":"2026-07-05T09:39:31.183041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:31.183041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OTchyh8Gv5FiqAk4wi2XlvlbsNFujOlOVTjKwTxAMOc+gRQl0/p+hMqnCy165laVhIwA+kiCy0ygTi/aWODlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:31.183626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a154d7410daa2e40e5d71894f97bf7ddb42d7b884580e23d9457b876cef366","sha256:b8bf3f5f78e78487bbb6c002ada0dfb92985386a341379947f88b661052cebea"],"state_sha256":"43e9ca08c77fce40c3ec8ec829e0e2c8ce1657f1d5ed1aa11776a7bdd0a9598f"}