{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FNUUT2P3U2QIECV4EGJT72JVIV","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":"55deea8b25f9f4b492fda3e95869ed5dee28cddfce82039ac0c88dc2cc094d2c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-14T04:20:19Z","title_canon_sha256":"06295dee55473ecc04a4c5d87ad7d02e0cf4229d4652e6ca5f8d789763c3628a"},"schema_version":"1.0","source":{"id":"2508.10333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10333","created_at":"2026-07-05T11:53:54Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10333v1","created_at":"2026-07-05T11:53:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10333","created_at":"2026-07-05T11:53:54Z"},{"alias_kind":"pith_short_12","alias_value":"FNUUT2P3U2QI","created_at":"2026-07-05T11:53:54Z"},{"alias_kind":"pith_short_16","alias_value":"FNUUT2P3U2QIECV4","created_at":"2026-07-05T11:53:54Z"},{"alias_kind":"pith_short_8","alias_value":"FNUUT2P3","created_at":"2026-07-05T11:53:54Z"}],"graph_snapshots":[{"event_id":"sha256:8556ab579a366ffd52c7b81b4163ad4dd32a43b438c45bf6d81936dfb60a81eb","target":"graph","created_at":"2026-07-05T11:53:54Z","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/2508.10333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the targ","authors_text":"Donglin Wang, Feilong Tang, Han Zhao, Haoang Li, Haodong Yan, Jiayi Chen, Pengxiang Ding, Wenxuan Song, Yuxin Huang, Ziyang Zhou","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-14T04:20:19Z","title":"ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10333","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:d439785649f36006e30cfbd4215f1241300de74d38b961b9b0f1273c4e17bb10","target":"record","created_at":"2026-07-05T11:53:54Z","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":"55deea8b25f9f4b492fda3e95869ed5dee28cddfce82039ac0c88dc2cc094d2c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-14T04:20:19Z","title_canon_sha256":"06295dee55473ecc04a4c5d87ad7d02e0cf4229d4652e6ca5f8d789763c3628a"},"schema_version":"1.0","source":{"id":"2508.10333","kind":"arxiv","version":1}},"canonical_sha256":"2b6949e9fba6a0820abc21933fe9354573f94639e0508f00b2e53bb6d070ee6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b6949e9fba6a0820abc21933fe9354573f94639e0508f00b2e53bb6d070ee6d","first_computed_at":"2026-07-05T11:53:54.160988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:54.160988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jgRP77WEUYOXcpgACsNPO9Mpj79adQvbHi71mZrbdNnnem5FAc4xA7bKVuBgLuhUcpQ2WLJWNEA0SNWm6G3zAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:54.161472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d439785649f36006e30cfbd4215f1241300de74d38b961b9b0f1273c4e17bb10","sha256:8556ab579a366ffd52c7b81b4163ad4dd32a43b438c45bf6d81936dfb60a81eb"],"state_sha256":"60fc0d849e287e3e1d452fe5b676712668bfcf210fac5f29793dc524dd639e69"}