{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A44NV72GXLFUGI7F2HKYB6TFBJ","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":"77f60b8402b63c706e549a080d5f6455acc614060a75fd2c7598052c2e5e96c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T18:50:36Z","title_canon_sha256":"cba63c6359ee293c74b185ea73345bb6b73910100b0f2da3cda22bfee7a13d9a"},"schema_version":"1.0","source":{"id":"2503.13646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13646","created_at":"2026-07-05T10:33:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13646v1","created_at":"2026-07-05T10:33:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13646","created_at":"2026-07-05T10:33:15Z"},{"alias_kind":"pith_short_12","alias_value":"A44NV72GXLFU","created_at":"2026-07-05T10:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"A44NV72GXLFUGI7F","created_at":"2026-07-05T10:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"A44NV72G","created_at":"2026-07-05T10:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:225830c852d3142209e68a6a0f7356aa77a8f9781e652ec8bd777037ad1b37f7","target":"graph","created_at":"2026-07-05T10:33:15Z","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/2503.13646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding fine-grained temporal dynamics is crucial in egocentric videos, where continuous streams capture frequent, close-up interactions with objects. In this work, we bring to light that current egocentric video question-answering datasets often include questions that can be answered using only few frames or commonsense reasoning, without being necessarily grounded in the actual video. Our analysis shows that state-of-the-art Multi-Modal Large Language Models (MLLMs) on these benchmarks achieve remarkably high performance using just text or a single frame as input. To address these limi","authors_text":"Achin Kulshrestha, Alessio Tonioni, Chiara Plizzari, Federico Tombari, Yongqin Xian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T18:50:36Z","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13646","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":"sha256:4596161342ad64d426c6ea36f259df4501081a45e5613804584b9697c7c55d49","target":"record","created_at":"2026-07-05T10:33:15Z","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":"77f60b8402b63c706e549a080d5f6455acc614060a75fd2c7598052c2e5e96c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T18:50:36Z","title_canon_sha256":"cba63c6359ee293c74b185ea73345bb6b73910100b0f2da3cda22bfee7a13d9a"},"schema_version":"1.0","source":{"id":"2503.13646","kind":"arxiv","version":1}},"canonical_sha256":"0738daff46bacb4323e5d1d580fa650a5983894415a69f45c9ec2ff2dbc2178a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0738daff46bacb4323e5d1d580fa650a5983894415a69f45c9ec2ff2dbc2178a","first_computed_at":"2026-07-05T10:33:15.606589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:15.606589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sVjdRwzYcjy+B3LW6kRc/FDlD5X5xaU9NGxOLGlLgTYqVc+TLp0Ay9KDzigx2nvQd6/+FJq5hkfqzEHSGk8SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:15.607360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4596161342ad64d426c6ea36f259df4501081a45e5613804584b9697c7c55d49","sha256:225830c852d3142209e68a6a0f7356aa77a8f9781e652ec8bd777037ad1b37f7"],"state_sha256":"44f247c5d9a4af3919626503a44f0377d88313faae9acb8a636ad7b772991e41"}