{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OP2TOXD63V2HB5TBGX5FRRLE46","short_pith_number":"pith:OP2TOXD6","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"},"canonical_sha256":"73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e","source":{"kind":"arxiv","id":"2603.10652","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10652","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10652v3","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10652","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"OP2TOXD63V2H","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"OP2TOXD63V2HB5TB","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"OP2TOXD6","created_at":"2026-07-01T01:17:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OP2TOXD63V2HB5TBGX5FRRLE46","target":"record","payload":{"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"},"canonical_sha256":"73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e","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"},"source_kind":"arxiv","source_id":"2603.10652","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pNxtCGjnoQndzMKx3lnPQulsZgkVdcNMEzpmSBchkIxzgEk1B8UgOzDvVTH2i/Tk2AKC8tEgVR7fmCXWH+wBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T11:46:40.202549Z"},"content_sha256":"a46f6af5fe7b30e9599c1dae9256ee308fc00d697903b15a0e225d87cec60b20","schema_version":"1.0","event_id":"sha256:a46f6af5fe7b30e9599c1dae9256ee308fc00d697903b15a0e225d87cec60b20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OP2TOXD63V2HB5TBGX5FRRLE46","target":"graph","payload":{"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"},"verdict_id":"31dae356-4c65-4159-bcf6-2dd3460b07d6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnAa/n5lX74dsrXJnPD+SH0utq5y5HCc329lRVK1bGxIt4GeHmIsSv9+R+g4wg8Yh+kxA/3mVEqKzxDXI0Q9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T11:46:40.203032Z"},"content_sha256":"2eb305472549a44187c61172d1341e9dbeaf0ff0bc02c17cf8b3705bb3d52098","schema_version":"1.0","event_id":"sha256:2eb305472549a44187c61172d1341e9dbeaf0ff0bc02c17cf8b3705bb3d52098"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/bundle.json","state_url":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OP2TOXD63V2HB5TBGX5FRRLE46/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-01T11:46:40Z","links":{"resolver":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46","bundle":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/bundle.json","state":"https://pith.science/pith/OP2TOXD63V2HB5TBGX5FRRLE46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OP2TOXD63V2HB5TBGX5FRRLE46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OP2TOXD63V2HB5TBGX5FRRLE46","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":"7b1e4d5cea334d2d13283ac45944e98fd4c1fe83dc2a752bb678dcae2aaf8b65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T11:10:52Z","title_canon_sha256":"88143994ffd17a5f2b1fdd0f1f3e61baa2d6281017b712fcdae67546a70be854"},"schema_version":"1.0","source":{"id":"2603.10652","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10652","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10652v3","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10652","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"OP2TOXD63V2H","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"OP2TOXD63V2HB5TB","created_at":"2026-07-01T01:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"OP2TOXD6","created_at":"2026-07-01T01:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:2eb305472549a44187c61172d1341e9dbeaf0ff0bc02c17cf8b3705bb3d52098","target":"graph","created_at":"2026-07-01T01:17:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances."}],"snapshot_sha256":"30e4223c1a65938739e9c9287f0b8e2ec1a97ee72693e656e43c391e022aa12b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b888605d871c9db4a22d7da66f0109db732707ecd01cc3715810f61647d0477d"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.10652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changgyu Boo, Jaehong Yoon, Yangfan He","cross_cats":["cs.AI"],"headline":"A consistency-based training method called ROVA improves video reasoning models' accuracy by at least 24 percent under real-world video disturbances.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T11:10:52Z","title":"Are Video Reasoning Models Ready to Go Outside?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10652","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T13:43:25.056614Z","id":"31dae356-4c65-4159-bcf6-2dd3460b07d6","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"31dae356-4c65-4159-bcf6-2dd3460b07d6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a46f6af5fe7b30e9599c1dae9256ee308fc00d697903b15a0e225d87cec60b20","target":"record","created_at":"2026-07-01T01:17:48Z","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":"7b1e4d5cea334d2d13283ac45944e98fd4c1fe83dc2a752bb678dcae2aaf8b65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T11:10:52Z","title_canon_sha256":"88143994ffd17a5f2b1fdd0f1f3e61baa2d6281017b712fcdae67546a70be854"},"schema_version":"1.0","source":{"id":"2603.10652","kind":"arxiv","version":3}},"canonical_sha256":"73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f5375c7edd7470f66135fa58c564e782c856c60e36ed902093db9a96bb626e","first_computed_at":"2026-07-01T01:17:48.687067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:48.687067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGH5AGTurkGKD3V3lbkUIf1feBMVUfq3Df4YbzLhZzOqLpHlVzD02oOjaSMPIB0LhyjqO8ejmI1SgNGDv3UFDw==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:48.687626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10652","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a46f6af5fe7b30e9599c1dae9256ee308fc00d697903b15a0e225d87cec60b20","sha256:2eb305472549a44187c61172d1341e9dbeaf0ff0bc02c17cf8b3705bb3d52098"],"state_sha256":"94a98aa10752049d5d3455ca28567c205b87d4712795c44547f9fb318d0c0299"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ti29GDTADz4SmcdRxopSBDMaVomDC7y1iEE16q06Y8b2D3+Uk9L4Yd8WWJnMqy8Q4U0QxH8mmht+sL/yijP2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T11:46:40.205361Z","bundle_sha256":"682098fd428cb3c286c071a8c4c980ba02963dead933b14ac2849154f590e3e6"}}