{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUQGXNOWOESRMT4GJZHSSKE6O2","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":"956e490ee04c17058ff8d4fbef8c127818ab01a7727f5a8efa96afb08c31c29f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-13T14:42:13Z","title_canon_sha256":"54f208c950d36b827107e351e6d06d6db7702d10984514bfe00aad57934320f1"},"schema_version":"1.0","source":{"id":"2405.07798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07798","created_at":"2026-07-05T08:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07798v2","created_at":"2026-07-05T08:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07798","created_at":"2026-07-05T08:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"BUQGXNOWOESR","created_at":"2026-07-05T08:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"BUQGXNOWOESRMT4G","created_at":"2026-07-05T08:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"BUQGXNOW","created_at":"2026-07-05T08:29:26Z"}],"graph_snapshots":[{"event_id":"sha256:f1dca57438ab7354445a490cab6f65b5ae5e3141abdca368473e92de2258653e","target":"graph","created_at":"2026-07-05T08:29:26Z","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/2405.07798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper undertakes an empirical study to revisit the latest advancements in Multimodal Large Language Models (MLLMs): Video Assistant. This study, namely FreeVA, aims to extend existing image-based MLLM to the video domain in a training-free manner. The study provides an essential, yet must-know baseline, and reveals several surprising findings: 1) FreeVA, leveraging only offline image-based MLLM without additional training, excels in zero-shot video question-answering (e.g., MSVD-QA, ActivityNet-QA, and MSRVTT-QA), even surpassing state-of-the-art methods that involve video instruction tun","authors_text":"Wenhao Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-13T14:42:13Z","title":"FreeVA: Offline MLLM as Training-Free Video Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07798","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":"sha256:58707ba70dc4ced5250f498c55d54971ca1c5f9c346df991c128d5f60c2990ab","target":"record","created_at":"2026-07-05T08:29:26Z","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":"956e490ee04c17058ff8d4fbef8c127818ab01a7727f5a8efa96afb08c31c29f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-13T14:42:13Z","title_canon_sha256":"54f208c950d36b827107e351e6d06d6db7702d10984514bfe00aad57934320f1"},"schema_version":"1.0","source":{"id":"2405.07798","kind":"arxiv","version":2}},"canonical_sha256":"0d206bb5d67125164f864e4f29289e76a8085601c94b2384c550a6929481cf3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d206bb5d67125164f864e4f29289e76a8085601c94b2384c550a6929481cf3d","first_computed_at":"2026-07-05T08:29:26.526668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:26.526668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iszq4r46ZcwtWsdfa2v9dAErfN1F1OvuRPcNT7jJEwzl8Sxx6DBIQYwBN1FVofaVT8gIhEVHBVgY5nCG7iadCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:26.527123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58707ba70dc4ced5250f498c55d54971ca1c5f9c346df991c128d5f60c2990ab","sha256:f1dca57438ab7354445a490cab6f65b5ae5e3141abdca368473e92de2258653e"],"state_sha256":"70c4c57a5dae4bcb9536d8c89762899275edf4dd9378bbe853995449ebcd1b31"}