{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GU2KKJLZZUXZF74WMBP3XYZQZ4","short_pith_number":"pith:GU2KKJLZ","schema_version":"1.0","canonical_sha256":"3534a52579cd2f92ff96605fbbe330cf1f9a7d8e7d165cd7c34efb600a207c8f","source":{"kind":"arxiv","id":"2607.08127","version":1},"attestation_state":"computed","paper":{"title":"Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Danfei Xu, Jiayuan Mao, Utkarsh A. Mishra, Xi Chen, Yang Liu, Yongxin Chen","submitted_at":"2026-07-09T05:56:08Z","abstract_excerpt":"Generative video foundation models exhibit strong compositional priors, yet world-action models (WAMs) and video-action models (VAMs) often lose these priors after finetuning on robotic action data. We refer to this discrepancy as the video-action generalization gap. In this paper, we systematically investigate this gap by evaluating a comprehensive design space of VAMs, demonstrating that standard design choices yield no emergent explanation pattern. To explain this behavior, we introduce the Temporal Ratio (TR), an attention-based measure of how strongly the action head relies on future late"},"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":"2607.08127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T05:56:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"fc70df8202432d0c46b2fef353b6df35f079ad20a6662fd82084f69fa2519622","abstract_canon_sha256":"30f3a1a65ea41c41eb84240d217e73ab6eaad8a7fda9e2b9fe91400162326daf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:27.404414Z","signature_b64":"tPSwOIhF1PId4+qwf+JbmeZCET8Ku66aoR+pKYZ6fPT3WWqrv9xUmdPSu+4XI6tVHpZIRVZap/sfpLEjCU0KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3534a52579cd2f92ff96605fbbe330cf1f9a7d8e7d165cd7c34efb600a207c8f","last_reissued_at":"2026-07-10T01:19:27.403788Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:27.403788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Danfei Xu, Jiayuan Mao, Utkarsh A. Mishra, Xi Chen, Yang Liu, Yongxin Chen","submitted_at":"2026-07-09T05:56:08Z","abstract_excerpt":"Generative video foundation models exhibit strong compositional priors, yet world-action models (WAMs) and video-action models (VAMs) often lose these priors after finetuning on robotic action data. We refer to this discrepancy as the video-action generalization gap. In this paper, we systematically investigate this gap by evaluating a comprehensive design space of VAMs, demonstrating that standard design choices yield no emergent explanation pattern. To explain this behavior, we introduce the Temporal Ratio (TR), an attention-based measure of how strongly the action head relies on future late"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08127","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/2607.08127/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":"2607.08127","created_at":"2026-07-10T01:19:27.403873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08127v1","created_at":"2026-07-10T01:19:27.403873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08127","created_at":"2026-07-10T01:19:27.403873+00:00"},{"alias_kind":"pith_short_12","alias_value":"GU2KKJLZZUXZ","created_at":"2026-07-10T01:19:27.403873+00:00"},{"alias_kind":"pith_short_16","alias_value":"GU2KKJLZZUXZF74W","created_at":"2026-07-10T01:19:27.403873+00:00"},{"alias_kind":"pith_short_8","alias_value":"GU2KKJLZ","created_at":"2026-07-10T01:19:27.403873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4","json":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4.json","graph_json":"https://pith.science/api/pith-number/GU2KKJLZZUXZF74WMBP3XYZQZ4/graph.json","events_json":"https://pith.science/api/pith-number/GU2KKJLZZUXZF74WMBP3XYZQZ4/events.json","paper":"https://pith.science/paper/GU2KKJLZ"},"agent_actions":{"view_html":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4","download_json":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4.json","view_paper":"https://pith.science/paper/GU2KKJLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08127&json=true","fetch_graph":"https://pith.science/api/pith-number/GU2KKJLZZUXZF74WMBP3XYZQZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/GU2KKJLZZUXZF74WMBP3XYZQZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4/action/storage_attestation","attest_author":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4/action/author_attestation","sign_citation":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4/action/citation_signature","submit_replication":"https://pith.science/pith/GU2KKJLZZUXZF74WMBP3XYZQZ4/action/replication_record"}},"created_at":"2026-07-10T01:19:27.403873+00:00","updated_at":"2026-07-10T01:19:27.403873+00:00"}