{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OP2TOXD63V2HB5TBGX5FRRLE46","short_pith_number":"pith:OP2TOXD6","schema_version":"1.0","canonical_sha256":"73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e","source":{"kind":"arxiv","id":"2603.10652","version":3},"attestation_state":"computed","paper":{"title":"Are Video Reasoning Models Ready to Go Outside?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changgyu Boo, Jaehong Yoon, Yangfan He","submitted_at":"2026-03-11T11:10:52Z","abstract_excerpt":"In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean, controlled (i.e., unperturbed) evaluation settings and real-world robustness. To address this limitation, we propose ROVA, a novel training framework that improves robustness by modeling a robustness-aware consistency reward under spatio-temporal corruptions. ROVA introduces a difficulty-aware online training strategy that prioritizes informative samples based o"},"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":true},"canonical_record":{"source":{"id":"2603.10652","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T11:10:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88143994ffd17a5f2b1fdd0f1f3e61baa2d6281017b712fcdae67546a70be854","abstract_canon_sha256":"7b1e4d5cea334d2d13283ac45944e98fd4c1fe83dc2a752bb678dcae2aaf8b65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:48.687626Z","signature_b64":"MGH5AGTurkGKD3V3lbkUIf1feBMVUfq3Df4YbzLhZzOqLpHlVzD02oOjaSMPIB0LhyjqO8ejmI1SgNGDv3UFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e","last_reissued_at":"2026-07-01T01:17:48.687067Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:48.687067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Video Reasoning Models Ready to Go Outside?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changgyu Boo, Jaehong Yoon, Yangfan He","submitted_at":"2026-03-11T11:10:52Z","abstract_excerpt":"In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean, controlled (i.e., unperturbed) evaluation settings and real-world robustness. To address this limitation, we propose ROVA, a novel training framework that improves robustness by modeling a robustness-aware consistency reward under spatio-temporal corruptions. ROVA introduces a difficulty-aware online training strategy that prioritizes informative samples based o"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ROVA effectively mitigates performance degradation, boosting relative accuracy by at least 24% and reasoning by over 9% compared with baseline models (QWen2.5/3-VL, InternVL2.5, Embodied-R). These gains transfer to clean standard benchmarks, yielding consistent improvements.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the specific spatio-temporal corruptions injected into PVRBench faithfully represent the distribution of real-world disturbances and that the self-reflective difficulty estimation does not introduce systematic bias in sample selection.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ROVA boosts video reasoning model accuracy by at least 24% and reasoning by over 9% under realistic perturbations via a new consistency reward and adaptive training, while PVRBench reveals up to 35% drops in existing models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"30e4223c1a65938739e9c9287f0b8e2ec1a97ee72693e656e43c391e022aa12b"},"source":{"id":"2603.10652","kind":"arxiv","version":3},"verdict":{"id":"31dae356-4c65-4159-bcf6-2dd3460b07d6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:43:25.056614Z","strongest_claim":"ROVA effectively mitigates performance degradation, boosting relative accuracy by at least 24% and reasoning by over 9% compared with baseline models (QWen2.5/3-VL, InternVL2.5, Embodied-R). These gains transfer to clean standard benchmarks, yielding consistent improvements.","one_line_summary":"ROVA boosts video reasoning model accuracy by at least 24% and reasoning by over 9% under realistic perturbations via a new consistency reward and adaptive training, while PVRBench reveals up to 35% drops in existing models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the specific spatio-temporal corruptions injected into PVRBench faithfully represent the distribution of real-world disturbances and that the self-reflective difficulty estimation does not introduce systematic bias in sample selection.","pith_extraction_headline":"A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.10652/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":2,"snapshot_sha256":"b888605d871c9db4a22d7da66f0109db732707ecd01cc3715810f61647d0477d"},"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":"2603.10652","created_at":"2026-07-01T01:17:48.687132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.10652v3","created_at":"2026-07-01T01:17:48.687132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10652","created_at":"2026-07-01T01:17:48.687132+00:00"},{"alias_kind":"pith_short_12","alias_value":"OP2TOXD63V2H","created_at":"2026-07-01T01:17:48.687132+00:00"},{"alias_kind":"pith_short_16","alias_value":"OP2TOXD63V2HB5TB","created_at":"2026-07-01T01:17:48.687132+00:00"},{"alias_kind":"pith_short_8","alias_value":"OP2TOXD6","created_at":"2026-07-01T01:17:48.687132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30026","citing_title":"MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46","json":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46.json","graph_json":"https://pith.science/api/pith-number/OP2TOXD63V2HB5TBGX5FRRLE46/graph.json","events_json":"https://pith.science/api/pith-number/OP2TOXD63V2HB5TBGX5FRRLE46/events.json","paper":"https://pith.science/paper/OP2TOXD6"},"agent_actions":{"view_html":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46","download_json":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46.json","view_paper":"https://pith.science/paper/OP2TOXD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.10652&json=true","fetch_graph":"https://pith.science/api/pith-number/OP2TOXD63V2HB5TBGX5FRRLE46/graph.json","fetch_events":"https://pith.science/api/pith-number/OP2TOXD63V2HB5TBGX5FRRLE46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/action/storage_attestation","attest_author":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/action/author_attestation","sign_citation":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/action/citation_signature","submit_replication":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/action/replication_record"}},"created_at":"2026-07-01T01:17:48.687132+00:00","updated_at":"2026-07-01T01:17:48.687132+00:00"}