{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TJL5VLZ3HTC3BCCED7WJ4SD5EI","short_pith_number":"pith:TJL5VLZ3","schema_version":"1.0","canonical_sha256":"9a57daaf3b3cc5b088441fec9e487d222226379d71f5077c1a780a103a400416","source":{"kind":"arxiv","id":"2508.13103","version":1},"attestation_state":"computed","paper":{"title":"Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Haonan Duan, Haoran Hao, Jifeng Dai, Tianyi Zhang, Yu Qiao, Zhi Hou","submitted_at":"2025-08-18T17:10:45Z","abstract_excerpt":"Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera perspectives, the models typically predict end-effector poses within the robot base coordinate frame, resulting in spatial inconsistencies. To mitigate this limitation, we introduce the Observation-Centric VLA (OC-VLA) framework, which grounds action predictions directly in the camera observation space. Leveraging the camera's extrinsic calibration matrix, OC-V"},"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":"2508.13103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-18T17:10:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"14440dae4ad375cb7a9e32262a67ad54dd1320c56dfb93f99623fcfc24a09015","abstract_canon_sha256":"021a10f0ec74431a56b5e8efe878d793c9d81d46f156641911d76411b4120313"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:32.472444Z","signature_b64":"m7LzXLrrAPecV3rXQbkY7Q7EqmntIQCUnOTcWVFrw+QRtqkY7X5e9bEcwbTXvK5xuWSg/EEScDYdcmjFPKrvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a57daaf3b3cc5b088441fec9e487d222226379d71f5077c1a780a103a400416","last_reissued_at":"2026-07-05T11:55:32.471930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:32.471930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Haonan Duan, Haoran Hao, Jifeng Dai, Tianyi Zhang, Yu Qiao, Zhi Hou","submitted_at":"2025-08-18T17:10:45Z","abstract_excerpt":"Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera perspectives, the models typically predict end-effector poses within the robot base coordinate frame, resulting in spatial inconsistencies. To mitigate this limitation, we introduce the Observation-Centric VLA (OC-VLA) framework, which grounds action predictions directly in the camera observation space. Leveraging the camera's extrinsic calibration matrix, OC-V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13103","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/2508.13103/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":"2508.13103","created_at":"2026-07-05T11:55:32.471990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13103v1","created_at":"2026-07-05T11:55:32.471990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13103","created_at":"2026-07-05T11:55:32.471990+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJL5VLZ3HTC3","created_at":"2026-07-05T11:55:32.471990+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJL5VLZ3HTC3BCCE","created_at":"2026-07-05T11:55:32.471990+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJL5VLZ3","created_at":"2026-07-05T11:55:32.471990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.17001","citing_title":"Unify Robot Actions in Camera Frame","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21241","citing_title":"CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI","json":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI.json","graph_json":"https://pith.science/api/pith-number/TJL5VLZ3HTC3BCCED7WJ4SD5EI/graph.json","events_json":"https://pith.science/api/pith-number/TJL5VLZ3HTC3BCCED7WJ4SD5EI/events.json","paper":"https://pith.science/paper/TJL5VLZ3"},"agent_actions":{"view_html":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI","download_json":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI.json","view_paper":"https://pith.science/paper/TJL5VLZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13103&json=true","fetch_graph":"https://pith.science/api/pith-number/TJL5VLZ3HTC3BCCED7WJ4SD5EI/graph.json","fetch_events":"https://pith.science/api/pith-number/TJL5VLZ3HTC3BCCED7WJ4SD5EI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI/action/storage_attestation","attest_author":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI/action/author_attestation","sign_citation":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI/action/citation_signature","submit_replication":"https://pith.science/pith/TJL5VLZ3HTC3BCCED7WJ4SD5EI/action/replication_record"}},"created_at":"2026-07-05T11:55:32.471990+00:00","updated_at":"2026-07-05T11:55:32.471990+00:00"}