{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SYOY6FNAXIDZN7IWE73J45CZ42","short_pith_number":"pith:SYOY6FNA","schema_version":"1.0","canonical_sha256":"961d8f15a0ba0796fd1627f69e7459e687916334ea2d0cccee71707e630720e4","source":{"kind":"arxiv","id":"2602.18020","version":2},"attestation_state":"computed","paper":{"title":"UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bowen Fang, Jiabing Yang, Jing Liu, Kai Wang, Liang Wang, Nianfeng Liu, Peiyan Li, Qisen Ma, Tao Yu, Xiangnan Wu, Yan Huang, Yingda Li, Yixiang Chen, Yuan Xu, Zhengbo Zhang, Zichen Wen, Ziheng He","submitted_at":"2026-02-20T06:22:21Z","abstract_excerpt":"Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for generalizable robotic manipulation. To enhance performance, existing methods often incorporate extra observation cues (e.g., depth maps, point clouds) or auxiliary modules (e.g., object detectors, encoders) to enable more precise and reliable task execution, yet these typically require costly data collection and additional training. Inspired by the finding that Feed-Forward Network (FFN) in language models can act a"},"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":"2602.18020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-20T06:22:21Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"e8cc0c8f966eca0e886326920bc77eaa1752f8f1d5df9a1f380bfc14a4203bf2","abstract_canon_sha256":"680fa375e33ddeb4a54be896e4d7f8afb4932a084e3b36fbac03863e28363e7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:14.813152Z","signature_b64":"vTkzFj+R+233wNVDCr21YFzjeJ3tI9/67Ko/OZTF5hcSGHFiIAdSx3jwJPgE6LIEbE1Ogw5iN8u7opvFjGPQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961d8f15a0ba0796fd1627f69e7459e687916334ea2d0cccee71707e630720e4","last_reissued_at":"2026-06-09T01:05:14.812651Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:14.812651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bowen Fang, Jiabing Yang, Jing Liu, Kai Wang, Liang Wang, Nianfeng Liu, Peiyan Li, Qisen Ma, Tao Yu, Xiangnan Wu, Yan Huang, Yingda Li, Yixiang Chen, Yuan Xu, Zhengbo Zhang, Zichen Wen, Ziheng He","submitted_at":"2026-02-20T06:22:21Z","abstract_excerpt":"Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for generalizable robotic manipulation. To enhance performance, existing methods often incorporate extra observation cues (e.g., depth maps, point clouds) or auxiliary modules (e.g., object detectors, encoders) to enable more precise and reliable task execution, yet these typically require costly data collection and additional training. Inspired by the finding that Feed-Forward Network (FFN) in language models can act a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18020","kind":"arxiv","version":2},"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/2602.18020/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":"2602.18020","created_at":"2026-06-09T01:05:14.812709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18020v2","created_at":"2026-06-09T01:05:14.812709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18020","created_at":"2026-06-09T01:05:14.812709+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYOY6FNAXIDZ","created_at":"2026-06-09T01:05:14.812709+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYOY6FNAXIDZN7IW","created_at":"2026-06-09T01:05:14.812709+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYOY6FNA","created_at":"2026-06-09T01:05:14.812709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.02965","citing_title":"Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42","json":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42.json","graph_json":"https://pith.science/api/pith-number/SYOY6FNAXIDZN7IWE73J45CZ42/graph.json","events_json":"https://pith.science/api/pith-number/SYOY6FNAXIDZN7IWE73J45CZ42/events.json","paper":"https://pith.science/paper/SYOY6FNA"},"agent_actions":{"view_html":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42","download_json":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42.json","view_paper":"https://pith.science/paper/SYOY6FNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18020&json=true","fetch_graph":"https://pith.science/api/pith-number/SYOY6FNAXIDZN7IWE73J45CZ42/graph.json","fetch_events":"https://pith.science/api/pith-number/SYOY6FNAXIDZN7IWE73J45CZ42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42/action/storage_attestation","attest_author":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42/action/author_attestation","sign_citation":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42/action/citation_signature","submit_replication":"https://pith.science/pith/SYOY6FNAXIDZN7IWE73J45CZ42/action/replication_record"}},"created_at":"2026-06-09T01:05:14.812709+00:00","updated_at":"2026-06-09T01:05:14.812709+00:00"}