{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CFTSVW6666ID677CTRHQPUP3JQ","short_pith_number":"pith:CFTSVW66","schema_version":"1.0","canonical_sha256":"11672adbdef7903f7fe29c4f07d1fb4c10bf5ed0e19d7f6c64f4a83bf59be691","source":{"kind":"arxiv","id":"2506.15666","version":1},"attestation_state":"computed","paper":{"title":"Vision in Action: Learning Active Perception from Human Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haoyu Xiong, Jeannette Bohg, Jimmy Wu, Shuran Song, Xiaomeng Xu, Yifan Hou","submitted_at":"2025-06-18T17:43:55Z","abstract_excerpt":"We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, and focusing) directly from human demonstrations. On the hardware side, ViA employs a simple yet effective 6-DoF robotic neck to enable flexible, human-like head movements. To capture human active perception strategies, we design a VR-based teleoperation interface that creates a shared observation space between the robot and the human operator. To mitigate VR motion sickness caused by latency in the robot's physical mo"},"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":"2506.15666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-18T17:43:55Z","cross_cats_sorted":[],"title_canon_sha256":"42d1de69078d067fb7dc21fb540d7da65a244e19f752d41ab86768706f1b91f5","abstract_canon_sha256":"071e043eefee6e7991edfe3f51b27f0e9300c0311690a567511c53708a39df82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:48.095642Z","signature_b64":"RJsW6x4XjkuxkEI/ma/7x01cZiEsdsySbgqO3q40iPDwK/OZ2X7Ix2dIw5LUG6UQlisxTIsb4wUSURRREYd3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11672adbdef7903f7fe29c4f07d1fb4c10bf5ed0e19d7f6c64f4a83bf59be691","last_reissued_at":"2026-07-05T11:23:48.095139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:48.095139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision in Action: Learning Active Perception from Human Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haoyu Xiong, Jeannette Bohg, Jimmy Wu, Shuran Song, Xiaomeng Xu, Yifan Hou","submitted_at":"2025-06-18T17:43:55Z","abstract_excerpt":"We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, and focusing) directly from human demonstrations. On the hardware side, ViA employs a simple yet effective 6-DoF robotic neck to enable flexible, human-like head movements. To capture human active perception strategies, we design a VR-based teleoperation interface that creates a shared observation space between the robot and the human operator. To mitigate VR motion sickness caused by latency in the robot's physical mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15666","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/2506.15666/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":"2506.15666","created_at":"2026-07-05T11:23:48.095196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15666v1","created_at":"2026-07-05T11:23:48.095196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15666","created_at":"2026-07-05T11:23:48.095196+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFTSVW6666ID","created_at":"2026-07-05T11:23:48.095196+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFTSVW6666ID677C","created_at":"2026-07-05T11:23:48.095196+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFTSVW66","created_at":"2026-07-05T11:23:48.095196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23625","citing_title":"Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22923","citing_title":"PanoVine: Whole-Body Visuomotor Control for Soft Growing Vine Robot","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02417","citing_title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12069","citing_title":"Tac-DINO: Learning Vision-Tactile Features with Patch Alignment","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18746","citing_title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18746","citing_title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15279","citing_title":"Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07607","citing_title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08534","citing_title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ","json":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ.json","graph_json":"https://pith.science/api/pith-number/CFTSVW6666ID677CTRHQPUP3JQ/graph.json","events_json":"https://pith.science/api/pith-number/CFTSVW6666ID677CTRHQPUP3JQ/events.json","paper":"https://pith.science/paper/CFTSVW66"},"agent_actions":{"view_html":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ","download_json":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ.json","view_paper":"https://pith.science/paper/CFTSVW66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15666&json=true","fetch_graph":"https://pith.science/api/pith-number/CFTSVW6666ID677CTRHQPUP3JQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CFTSVW6666ID677CTRHQPUP3JQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ/action/storage_attestation","attest_author":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ/action/author_attestation","sign_citation":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ/action/citation_signature","submit_replication":"https://pith.science/pith/CFTSVW6666ID677CTRHQPUP3JQ/action/replication_record"}},"created_at":"2026-07-05T11:23:48.095196+00:00","updated_at":"2026-07-05T11:23:48.095196+00:00"}