{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GU2KKJLZZUXZF74WMBP3XYZQZ4","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":"30f3a1a65ea41c41eb84240d217e73ab6eaad8a7fda9e2b9fe91400162326daf","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T05:56:08Z","title_canon_sha256":"fc70df8202432d0c46b2fef353b6df35f079ad20a6662fd82084f69fa2519622"},"schema_version":"1.0","source":{"id":"2607.08127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08127","created_at":"2026-07-10T01:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08127v1","created_at":"2026-07-10T01:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08127","created_at":"2026-07-10T01:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"GU2KKJLZZUXZ","created_at":"2026-07-10T01:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"GU2KKJLZZUXZF74W","created_at":"2026-07-10T01:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"GU2KKJLZ","created_at":"2026-07-10T01:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:b8182e162930efd79228ecf7597790f62b0dec39fb55f6632cae187c8acbb967","target":"graph","created_at":"2026-07-10T01:19:27Z","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/2607.08127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Danfei Xu, Jiayuan Mao, Utkarsh A. Mishra, Xi Chen, Yang Liu, Yongxin Chen","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T05:56:08Z","title":"Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08127","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":"sha256:3c83a7e7f2e317353dcf11e93143e8d282d4a0450aa374591248541037ee2ad7","target":"record","created_at":"2026-07-10T01:19:27Z","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":"30f3a1a65ea41c41eb84240d217e73ab6eaad8a7fda9e2b9fe91400162326daf","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T05:56:08Z","title_canon_sha256":"fc70df8202432d0c46b2fef353b6df35f079ad20a6662fd82084f69fa2519622"},"schema_version":"1.0","source":{"id":"2607.08127","kind":"arxiv","version":1}},"canonical_sha256":"3534a52579cd2f92ff96605fbbe330cf1f9a7d8e7d165cd7c34efb600a207c8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3534a52579cd2f92ff96605fbbe330cf1f9a7d8e7d165cd7c34efb600a207c8f","first_computed_at":"2026-07-10T01:19:27.403788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:27.403788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tPSwOIhF1PId4+qwf+JbmeZCET8Ku66aoR+pKYZ6fPT3WWqrv9xUmdPSu+4XI6tVHpZIRVZap/sfpLEjCU0KCg==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:27.404414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c83a7e7f2e317353dcf11e93143e8d282d4a0450aa374591248541037ee2ad7","sha256:b8182e162930efd79228ecf7597790f62b0dec39fb55f6632cae187c8acbb967"],"state_sha256":"47c1ed56d8a8462c054c6144e4d4111b46eaedcc551a3beddad5c8332536e90e"}