{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O74H2BXZ2YUU6XLYVOOTHVCVSD","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":"a6bf511fee1d57ffb0e702906a09fea3c23f5508253b5636a3f6905ccf6e9130","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T07:54:37Z","title_canon_sha256":"14618f84a5c86422a84034ad26e07057459afd449c4c37518ffcd1ed1f34ba25"},"schema_version":"1.0","source":{"id":"2305.13786","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13786","created_at":"2026-07-05T07:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13786v2","created_at":"2026-07-05T07:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13786","created_at":"2026-07-05T07:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"O74H2BXZ2YUU","created_at":"2026-07-05T07:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"O74H2BXZ2YUU6XLY","created_at":"2026-07-05T07:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"O74H2BXZ","created_at":"2026-07-05T07:07:10Z"}],"graph_snapshots":[{"event_id":"sha256:e0fd54f6400f11fa72f20c742b07d7f748f5cf1a5ad37a6cb7dbef0c1b382736","target":"graph","created_at":"2026-07-05T07:07:10Z","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/2305.13786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, SeViLA, or GPT-4). Compared to existing benchmarks that focus on computational tasks (e.g. classification, detection or tracking), the Perception Test focuses on skills (Memory, Abstraction, Physics, Semantics) and types of reasoning (descriptive, explanatory, predictive, counterfactual) across video, audio, and text modalities, to provide a comprehensive and efficient evaluation tool. The benchmark probes pre-trained models for ","authors_text":"Adri\\`a Recasens Continente, Alex Frechette, Andrew Zisserman, Ankush Gupta, Antoine Miech, Carl Doersch, Dima Damen, Dylan Banarse, Hanna Klimczak, Jo\\~ao Carreira, Joseph Heyward, Junlin Zhang, Larisa Markeeva, Lucas Smaira, Mateusz Malinowski, Raphael Koster, Simon Osindero, Skanda Koppula, Stephanie Winkler, Tatiana Matejovicova, Viorica P\\u{a}tr\\u{a}ucean, Yi Yang, Yury Sulsky, Yusuf Aytar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T07:54:37Z","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13786","kind":"arxiv","version":2},"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:dc8e751681f02292a8663d7e02b0ab2b8e52865b6ecea0ae425ec189d05ca3fa","target":"record","created_at":"2026-07-05T07:07:10Z","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":"a6bf511fee1d57ffb0e702906a09fea3c23f5508253b5636a3f6905ccf6e9130","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T07:54:37Z","title_canon_sha256":"14618f84a5c86422a84034ad26e07057459afd449c4c37518ffcd1ed1f34ba25"},"schema_version":"1.0","source":{"id":"2305.13786","kind":"arxiv","version":2}},"canonical_sha256":"77f87d06f9d6294f5d78ab9d33d45590e35ca69ef71af6e72455386e1e4d7e41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77f87d06f9d6294f5d78ab9d33d45590e35ca69ef71af6e72455386e1e4d7e41","first_computed_at":"2026-07-05T07:07:10.311140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:10.311140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ms2eUzWmaG/3v8l8H/E1z3rhFQVaDAe5SWmeWNRk2UUHBwUKRH1M8J8cc6TjLTcl4oVecVgJGPl8mi5gHRKSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:10.311697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13786","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc8e751681f02292a8663d7e02b0ab2b8e52865b6ecea0ae425ec189d05ca3fa","sha256:e0fd54f6400f11fa72f20c742b07d7f748f5cf1a5ad37a6cb7dbef0c1b382736"],"state_sha256":"f34ad5d0805cec1cb3e470faef53a86118e38fc39c58e13cc83798f4b0c4c9c5"}