{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RKS3IJGLIOARK3BCGBJFNR25N5","short_pith_number":"pith:RKS3IJGL","canonical_record":{"source":{"id":"2607.25516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-28T09:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"bdde9e23bd9ef8d6bae8875cff6b40305eaba3a6fd6eb0af4da3efc2490e254c","abstract_canon_sha256":"25f2027d3c9cc9f4e70ca3ac7fdf7d87aa85a5e369e2c902439ca25b6e3a1d36"},"schema_version":"1.0"},"canonical_sha256":"8aa5b424cb4381156c22305256c75d6f579374be98fbf3be8a8cdeca48323086","source":{"kind":"arxiv","id":"2607.25516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25516","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25516v1","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25516","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"RKS3IJGLIOAR","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"RKS3IJGLIOARK3BC","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"RKS3IJGL","created_at":"2026-07-29T01:25:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RKS3IJGLIOARK3BCGBJFNR25N5","target":"record","payload":{"canonical_record":{"source":{"id":"2607.25516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-28T09:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"bdde9e23bd9ef8d6bae8875cff6b40305eaba3a6fd6eb0af4da3efc2490e254c","abstract_canon_sha256":"25f2027d3c9cc9f4e70ca3ac7fdf7d87aa85a5e369e2c902439ca25b6e3a1d36"},"schema_version":"1.0"},"canonical_sha256":"8aa5b424cb4381156c22305256c75d6f579374be98fbf3be8a8cdeca48323086","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:44.552416Z","signature_b64":"Fxy4TwKcrMIQWZDlFrHaLPbn7RpC8gMsmku5B4Uu/L6PN7E/uWVU4yZmjOB2kcOvHyjhBHPxXB0GO+vrbI4zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa5b424cb4381156c22305256c75d6f579374be98fbf3be8a8cdeca48323086","last_reissued_at":"2026-07-29T01:25:44.551466Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:44.551466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.25516","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T01:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQGN6t7XUwsbaq0xeJExgUmJPGWC3oxhAOjyWpcHcgkQfDgl6CigsRKTupyP6IpgueCC2IhR7HyiASJJVm+EDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:23:04.808833Z"},"content_sha256":"b8d5515469ad9075608ad8bf672a3816b1756e4b4811ff95d60e8a4669602735","schema_version":"1.0","event_id":"sha256:b8d5515469ad9075608ad8bf672a3816b1756e4b4811ff95d60e8a4669602735"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RKS3IJGLIOARK3BCGBJFNR25N5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fan Li, Gao Zhi, Haoyu Zhang, Jin Chen, Kun Wu, Mingyang Gao, Yongchun Liu, Yuwei Wu, Zhenxin Diao","submitted_at":"2026-07-28T09:56:42Z","abstract_excerpt":"Vision-language-action (VLA) models predict sequential actions to execute tasks specified by language instructions, conditioned on visual observations and proprioceptive states. However, how to fuse modalities in VLA models remains an open problem, since robot manipulation involves dynamic phases, such as long-distance movements and close-range interactions, in which the importance of visual observations may vary over time. In this paper, we propose an infer-diagnose-refine (IDR) framework, a model-agnostic framework that can be integrated with diverse VLA architectures for refining action pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25516","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/2607.25516/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T01:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqzSoQAoAZOI5wFYX+naO2h1TGARD0vP2HTLBumweVsxpZn+UTgZiV3PU6YA7e1l3XFObP9bk93v2Tu8rMB7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:23:04.809893Z"},"content_sha256":"b923b1e54265cc8a1129cc90629d47b8d63fb459615c573ba08d02c869d74ce6","schema_version":"1.0","event_id":"sha256:b923b1e54265cc8a1129cc90629d47b8d63fb459615c573ba08d02c869d74ce6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKS3IJGLIOARK3BCGBJFNR25N5/bundle.json","state_url":"https://pith.science/pith/RKS3IJGLIOARK3BCGBJFNR25N5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKS3IJGLIOARK3BCGBJFNR25N5/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":"2026-08-04T08:23:04Z","links":{"resolver":"https://pith.science/pith/RKS3IJGLIOARK3BCGBJFNR25N5","bundle":"https://pith.science/pith/RKS3IJGLIOARK3BCGBJFNR25N5/bundle.json","state":"https://pith.science/pith/RKS3IJGLIOARK3BCGBJFNR25N5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKS3IJGLIOARK3BCGBJFNR25N5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RKS3IJGLIOARK3BCGBJFNR25N5","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":"25f2027d3c9cc9f4e70ca3ac7fdf7d87aa85a5e369e2c902439ca25b6e3a1d36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-28T09:56:42Z","title_canon_sha256":"bdde9e23bd9ef8d6bae8875cff6b40305eaba3a6fd6eb0af4da3efc2490e254c"},"schema_version":"1.0","source":{"id":"2607.25516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25516","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25516v1","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25516","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"RKS3IJGLIOAR","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"RKS3IJGLIOARK3BC","created_at":"2026-07-29T01:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"RKS3IJGL","created_at":"2026-07-29T01:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:b923b1e54265cc8a1129cc90629d47b8d63fb459615c573ba08d02c869d74ce6","target":"graph","created_at":"2026-07-29T01:25:44Z","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/2607.25516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action (VLA) models predict sequential actions to execute tasks specified by language instructions, conditioned on visual observations and proprioceptive states. However, how to fuse modalities in VLA models remains an open problem, since robot manipulation involves dynamic phases, such as long-distance movements and close-range interactions, in which the importance of visual observations may vary over time. In this paper, we propose an infer-diagnose-refine (IDR) framework, a model-agnostic framework that can be integrated with diverse VLA architectures for refining action pre","authors_text":"Fan Li, Gao Zhi, Haoyu Zhang, Jin Chen, Kun Wu, Mingyang Gao, Yongchun Liu, Yuwei Wu, Zhenxin Diao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-28T09:56:42Z","title":"A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25516","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:b8d5515469ad9075608ad8bf672a3816b1756e4b4811ff95d60e8a4669602735","target":"record","created_at":"2026-07-29T01:25:44Z","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":"25f2027d3c9cc9f4e70ca3ac7fdf7d87aa85a5e369e2c902439ca25b6e3a1d36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-28T09:56:42Z","title_canon_sha256":"bdde9e23bd9ef8d6bae8875cff6b40305eaba3a6fd6eb0af4da3efc2490e254c"},"schema_version":"1.0","source":{"id":"2607.25516","kind":"arxiv","version":1}},"canonical_sha256":"8aa5b424cb4381156c22305256c75d6f579374be98fbf3be8a8cdeca48323086","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aa5b424cb4381156c22305256c75d6f579374be98fbf3be8a8cdeca48323086","first_computed_at":"2026-07-29T01:25:44.551466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:25:44.551466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fxy4TwKcrMIQWZDlFrHaLPbn7RpC8gMsmku5B4Uu/L6PN7E/uWVU4yZmjOB2kcOvHyjhBHPxXB0GO+vrbI4zAw==","signature_status":"signed_v1","signed_at":"2026-07-29T01:25:44.552416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8d5515469ad9075608ad8bf672a3816b1756e4b4811ff95d60e8a4669602735","sha256:b923b1e54265cc8a1129cc90629d47b8d63fb459615c573ba08d02c869d74ce6"],"state_sha256":"3d741bbc21a652a1cc89604239c6c73aae74a399843c8085dac90607d41f62bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSb2NCj46Eda5msNB+qCXtGIKpHQWFnyB6hrvU+UUXACVWCsjgeDSZTsu+qpycgqMI9KrQEcaQncZwYQ+9XgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:23:04.821937Z","bundle_sha256":"2f5e7b725c853b844d12bdc4fe8a04b69c0907ee7ea6a6981250015820ff8871"}}