{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FCJV6Y2QU25NVE4DBXSA6RC3LE","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":"d36be731bdd223e9ade30723526e310ac1b48bb514c717d006f44ba2f395b0e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T10:42:21Z","title_canon_sha256":"4c041b3be70eced343e70126db467bf6d25f1b71cdfab531fc8fe441a2ac2676"},"schema_version":"1.0","source":{"id":"2406.10889","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10889","created_at":"2026-07-05T10:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10889v2","created_at":"2026-07-05T10:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10889","created_at":"2026-07-05T10:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"FCJV6Y2QU25N","created_at":"2026-07-05T10:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"FCJV6Y2QU25NVE4D","created_at":"2026-07-05T10:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"FCJV6Y2Q","created_at":"2026-07-05T10:41:13Z"}],"graph_snapshots":[{"event_id":"sha256:fd3318df5d7628016d7f4092dc8eae3aeee5896003a6ba444d36721aba44fe71","target":"graph","created_at":"2026-07-05T10:41:13Z","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/2406.10889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental aspect of compositional reasoning in a video is associating people and their actions across time. Recent years have seen great progress in general-purpose vision or video models and a move towards long-video understanding. While exciting, we take a step back and ask: are current models good at compositional reasoning on short videos? To this end, we introduce VELOCITI, a benchmark to study Video-LLMs by disentangling and assessing the comprehension of agents, actions, and their associations across multiple events. We adopt the Video-Language Entailment setup and propose StrictVLE","authors_text":"Darshana Saravanan, Darshan Singh, Makarand Tapaswi, Varun Gupta, Vineet Gandhi, Zeeshan Khan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T10:42:21Z","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10889","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":"sha256:414b26948328a46ad5dd4369662090aea556d56d6e6a83ae46acc5a1a3939046","target":"record","created_at":"2026-07-05T10:41:13Z","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":"d36be731bdd223e9ade30723526e310ac1b48bb514c717d006f44ba2f395b0e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T10:42:21Z","title_canon_sha256":"4c041b3be70eced343e70126db467bf6d25f1b71cdfab531fc8fe441a2ac2676"},"schema_version":"1.0","source":{"id":"2406.10889","kind":"arxiv","version":2}},"canonical_sha256":"28935f6350a6bada93830de40f445b590d2a1f6bc89191c6dd8ccdca1ac04ac4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28935f6350a6bada93830de40f445b590d2a1f6bc89191c6dd8ccdca1ac04ac4","first_computed_at":"2026-07-05T10:41:13.113422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:13.113422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hrCWuNFzanWxPXYyOcZQzL44cIbEOGZtgwQDilDwS+lQMIE3lyDuMhrucihI/b+wNvFfC4KZT//JFZvl0tdqAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:13.113901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10889","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:414b26948328a46ad5dd4369662090aea556d56d6e6a83ae46acc5a1a3939046","sha256:fd3318df5d7628016d7f4092dc8eae3aeee5896003a6ba444d36721aba44fe71"],"state_sha256":"ef7afda35ec2ff0c60a7bbf8bc266e1e878ddddcbed5065b87741d99e68e3bf2"}