{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A44NV72GXLFUGI7F2HKYB6TFBJ","short_pith_number":"pith:A44NV72G","schema_version":"1.0","canonical_sha256":"0738daff46bacb4323e5d1d580fa650a5983894415a69f45c9ec2ff2dbc2178a","source":{"kind":"arxiv","id":"2503.13646","version":1},"attestation_state":"computed","paper":{"title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achin Kulshrestha, Alessio Tonioni, Chiara Plizzari, Federico Tombari, Yongqin Xian","submitted_at":"2025-03-17T18:50:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.13646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T18:50:36Z","cross_cats_sorted":[],"title_canon_sha256":"cba63c6359ee293c74b185ea73345bb6b73910100b0f2da3cda22bfee7a13d9a","abstract_canon_sha256":"77f60b8402b63c706e549a080d5f6455acc614060a75fd2c7598052c2e5e96c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:15.607360Z","signature_b64":"sVjdRwzYcjy+B3LW6kRc/FDlD5X5xaU9NGxOLGlLgTYqVc+TLp0Ay9KDzigx2nvQd6/+FJq5hkfqzEHSGk8SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0738daff46bacb4323e5d1d580fa650a5983894415a69f45c9ec2ff2dbc2178a","last_reissued_at":"2026-07-05T10:33:15.606589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:15.606589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achin Kulshrestha, Alessio Tonioni, Chiara Plizzari, Federico Tombari, Yongqin Xian","submitted_at":"2025-03-17T18:50:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13646","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.13646/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.13646","created_at":"2026-07-05T10:33:15.606700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13646v1","created_at":"2026-07-05T10:33:15.606700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13646","created_at":"2026-07-05T10:33:15.606700+00:00"},{"alias_kind":"pith_short_12","alias_value":"A44NV72GXLFU","created_at":"2026-07-05T10:33:15.606700+00:00"},{"alias_kind":"pith_short_16","alias_value":"A44NV72GXLFUGI7F","created_at":"2026-07-05T10:33:15.606700+00:00"},{"alias_kind":"pith_short_8","alias_value":"A44NV72G","created_at":"2026-07-05T10:33:15.606700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05259","citing_title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31557","citing_title":"EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07180","citing_title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ","json":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ.json","graph_json":"https://pith.science/api/pith-number/A44NV72GXLFUGI7F2HKYB6TFBJ/graph.json","events_json":"https://pith.science/api/pith-number/A44NV72GXLFUGI7F2HKYB6TFBJ/events.json","paper":"https://pith.science/paper/A44NV72G"},"agent_actions":{"view_html":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ","download_json":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ.json","view_paper":"https://pith.science/paper/A44NV72G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13646&json=true","fetch_graph":"https://pith.science/api/pith-number/A44NV72GXLFUGI7F2HKYB6TFBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/A44NV72GXLFUGI7F2HKYB6TFBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ/action/storage_attestation","attest_author":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ/action/author_attestation","sign_citation":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ/action/citation_signature","submit_replication":"https://pith.science/pith/A44NV72GXLFUGI7F2HKYB6TFBJ/action/replication_record"}},"created_at":"2026-07-05T10:33:15.606700+00:00","updated_at":"2026-07-05T10:33:15.606700+00:00"}