{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3GSJK6GSFS2GAX4POBY7KVCELT","short_pith_number":"pith:3GSJK6GS","schema_version":"1.0","canonical_sha256":"d9a49578d22cb4605f8f7071f554445ceb04154f43e517def84b8431805a01cc","source":{"kind":"arxiv","id":"2607.29622","version":1},"attestation_state":"computed","paper":{"title":"RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Aleksandar Taranovic, C. F. Maximilian Nagy, Ge Li, Gerhard Neumann, Longrui Chen, Niklas Freymuth, Peiran Sun, Qian Wang, Tao Chen, Weiran Liao, Yucheng Tan","submitted_at":"2026-07-31T16:56:33Z","abstract_excerpt":"Visual imitation learning enables robots to acquire visuomotor skills directly from images, yet RGB observations lack explicit geometric cues, making learned policies brittle to camera perturbations. To address this, we propose \\textbf{Ray-conditioned Vision Transformer Encoder (RayViT)}, a lightweight architecture that injects camera geometry into pretrained ViT backbones. RayViT represents camera geometry as a Pl\\\"ucker ray map, patchifies it into ray features, and uses gated cross-attention to produce a ray-conditioned class token. These ray features are added as dense positional embeddings"},"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":"2607.29622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-31T16:56:33Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c5be73fe78ccbdb9db59b6ac8c385d5aa999d526caa6f68a907dc7b39a502837","abstract_canon_sha256":"1aed950c2c87dc9bfa30498f50cabd6716b5dffc1b8836d63a148b3eec0e279b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:40:43.235082Z","signature_b64":"P97ThYhRhXKU98y21YfLyy557V2PZvn+DSUqCSfAgmlPE72KdV1kChBDbUxnI2QKxv+poBQOTsQkry+Sps3wBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a49578d22cb4605f8f7071f554445ceb04154f43e517def84b8431805a01cc","last_reissued_at":"2026-08-03T01:40:43.233613Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:40:43.233613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Aleksandar Taranovic, C. F. Maximilian Nagy, Ge Li, Gerhard Neumann, Longrui Chen, Niklas Freymuth, Peiran Sun, Qian Wang, Tao Chen, Weiran Liao, Yucheng Tan","submitted_at":"2026-07-31T16:56:33Z","abstract_excerpt":"Visual imitation learning enables robots to acquire visuomotor skills directly from images, yet RGB observations lack explicit geometric cues, making learned policies brittle to camera perturbations. To address this, we propose \\textbf{Ray-conditioned Vision Transformer Encoder (RayViT)}, a lightweight architecture that injects camera geometry into pretrained ViT backbones. RayViT represents camera geometry as a Pl\\\"ucker ray map, patchifies it into ray features, and uses gated cross-attention to produce a ray-conditioned class token. These ray features are added as dense positional embeddings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29622","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/2607.29622/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":"2607.29622","created_at":"2026-08-03T01:40:43.234466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29622v1","created_at":"2026-08-03T01:40:43.234466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29622","created_at":"2026-08-03T01:40:43.234466+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GSJK6GSFS2G","created_at":"2026-08-03T01:40:43.234466+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GSJK6GSFS2GAX4P","created_at":"2026-08-03T01:40:43.234466+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GSJK6GS","created_at":"2026-08-03T01:40:43.234466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT","json":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT.json","graph_json":"https://pith.science/api/pith-number/3GSJK6GSFS2GAX4POBY7KVCELT/graph.json","events_json":"https://pith.science/api/pith-number/3GSJK6GSFS2GAX4POBY7KVCELT/events.json","paper":"https://pith.science/paper/3GSJK6GS"},"agent_actions":{"view_html":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT","download_json":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT.json","view_paper":"https://pith.science/paper/3GSJK6GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29622&json=true","fetch_graph":"https://pith.science/api/pith-number/3GSJK6GSFS2GAX4POBY7KVCELT/graph.json","fetch_events":"https://pith.science/api/pith-number/3GSJK6GSFS2GAX4POBY7KVCELT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT/action/storage_attestation","attest_author":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT/action/author_attestation","sign_citation":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT/action/citation_signature","submit_replication":"https://pith.science/pith/3GSJK6GSFS2GAX4POBY7KVCELT/action/replication_record"}},"created_at":"2026-08-03T01:40:43.234466+00:00","updated_at":"2026-08-03T01:40:43.234466+00:00"}