{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZANUH654ERIVIWZZTD77UTDT7F","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":"9a6ab2ece62720f04de6cae3afd93937c559dcf5c686c072c3634b076e53a67a","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T16:58:23Z","title_canon_sha256":"d1de97c4800e27a769a78017538b8fdf8988d4d8b720dc687e050306c568c9a7"},"schema_version":"1.0","source":{"id":"2504.04550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04550","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04550v1","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04550","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZANUH654ERIV","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZANUH654ERIVIWZZ","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZANUH654","created_at":"2026-07-05T10:45:25Z"}],"graph_snapshots":[{"event_id":"sha256:bf5453c34cfcffa9e3f9e0e0d705be3b429e0b781d987f6418546895f121a7ad","target":"graph","created_at":"2026-07-05T10:45:25Z","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/2504.04550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and specialized challenges like frequent camera movement. This paper systematically evaluates both proprietary and open-source Multimodal Large Language Models (MLLMs) on QaEgo4Dv2 - a refined dataset of egocentric videos derived from QaEgo4D. Four popular MLLMs (GPT-4o, Gemini-1.5-Pro, Video-LLaVa-7B and Qwen2-VL-7B-Instruct) are assessed using zero-shot and fine-tuned approaches for both OpenQA and CloseQA settings. We introduce QaEgo4Dv2 to mitigate annotation noise","authors_text":"Alkesh Patel, Vibhav Chitalia, Yinfei Yang","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T16:58:23Z","title":"Advancing Egocentric Video Question Answering with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04550","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":"sha256:83230449d671f67201c7fe9a5262ec31a2d4d96de8c52b7f719722e6a54d0f84","target":"record","created_at":"2026-07-05T10:45:25Z","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":"9a6ab2ece62720f04de6cae3afd93937c559dcf5c686c072c3634b076e53a67a","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T16:58:23Z","title_canon_sha256":"d1de97c4800e27a769a78017538b8fdf8988d4d8b720dc687e050306c568c9a7"},"schema_version":"1.0","source":{"id":"2504.04550","kind":"arxiv","version":1}},"canonical_sha256":"c81b43fbbc2451545b3998fffa4c73f948c906e289693fc6360a1fb6350ae7b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c81b43fbbc2451545b3998fffa4c73f948c906e289693fc6360a1fb6350ae7b9","first_computed_at":"2026-07-05T10:45:25.887022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:25.887022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EMBr7R19FtSqfwY1UUyqMdlK8swQU2mTX4L3Mu9MIYQx2fk00LbBREzfdzGYgV1uoKpegDX+Aa9P4ALatDrRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:25.887438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83230449d671f67201c7fe9a5262ec31a2d4d96de8c52b7f719722e6a54d0f84","sha256:bf5453c34cfcffa9e3f9e0e0d705be3b429e0b781d987f6418546895f121a7ad"],"state_sha256":"70b371c6533d65e895d4298320629394df7be9ca340b8f2115be62e82990c676"}