{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZNPSAWM53EE5WPUSYPI32TPDSH","short_pith_number":"pith:ZNPSAWM5","schema_version":"1.0","canonical_sha256":"cb5f20599dd909db3e92c3d1bd4de391f1db5bf021e88d1d403dde70f2c4f393","source":{"kind":"arxiv","id":"2411.17458","version":1},"attestation_state":"computed","paper":{"title":"Spatially Visual Perception for End-to-End Robotic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiahuan Yan, Luhui Hu, Travis Davies, Xiang Chen, Yiqi Huang, Yueting Zhuang, Yu Tian","submitted_at":"2024-11-26T14:23:42Z","abstract_excerpt":"Recent advances in imitation learning have shown significant promise for robotic control and embodied intelligence. However, achieving robust generalization across diverse mounted camera observations remains a critical challenge. In this paper, we introduce a video-based spatial perception framework that leverages 3D spatial representations to address environmental variability, with a focus on handling lighting changes. Our approach integrates a novel image augmentation technique, AugBlender, with a state-of-the-art monocular depth estimation model trained on internet-scale data. Together, the"},"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":"2411.17458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:23:42Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"dc200bc199a9c0d3a28fc166a9051ebf27fab4ff677bcb3f733611afcde39c58","abstract_canon_sha256":"13cf20c94dc8b46f9b7a576248ad544cf7a168ba8fabf596d5b28e81d2fb65dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:47.498275Z","signature_b64":"GVafrRFHip94YEk2hcb98J3QQiXQfRrHj0rMDZdgl+lHnoN5yx6Dcnk5d4MtpL3kxx48QVsG00TGDIjGJATaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb5f20599dd909db3e92c3d1bd4de391f1db5bf021e88d1d403dde70f2c4f393","last_reissued_at":"2026-07-05T09:40:47.497788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:47.497788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatially Visual Perception for End-to-End Robotic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiahuan Yan, Luhui Hu, Travis Davies, Xiang Chen, Yiqi Huang, Yueting Zhuang, Yu Tian","submitted_at":"2024-11-26T14:23:42Z","abstract_excerpt":"Recent advances in imitation learning have shown significant promise for robotic control and embodied intelligence. However, achieving robust generalization across diverse mounted camera observations remains a critical challenge. In this paper, we introduce a video-based spatial perception framework that leverages 3D spatial representations to address environmental variability, with a focus on handling lighting changes. Our approach integrates a novel image augmentation technique, AugBlender, with a state-of-the-art monocular depth estimation model trained on internet-scale data. Together, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17458","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/2411.17458/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":"2411.17458","created_at":"2026-07-05T09:40:47.497839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17458v1","created_at":"2026-07-05T09:40:47.497839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17458","created_at":"2026-07-05T09:40:47.497839+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNPSAWM53EE5","created_at":"2026-07-05T09:40:47.497839+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNPSAWM53EE5WPUS","created_at":"2026-07-05T09:40:47.497839+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNPSAWM5","created_at":"2026-07-05T09:40:47.497839+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/ZNPSAWM53EE5WPUSYPI32TPDSH","json":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH.json","graph_json":"https://pith.science/api/pith-number/ZNPSAWM53EE5WPUSYPI32TPDSH/graph.json","events_json":"https://pith.science/api/pith-number/ZNPSAWM53EE5WPUSYPI32TPDSH/events.json","paper":"https://pith.science/paper/ZNPSAWM5"},"agent_actions":{"view_html":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH","download_json":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH.json","view_paper":"https://pith.science/paper/ZNPSAWM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17458&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNPSAWM53EE5WPUSYPI32TPDSH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNPSAWM53EE5WPUSYPI32TPDSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH/action/storage_attestation","attest_author":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH/action/author_attestation","sign_citation":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH/action/citation_signature","submit_replication":"https://pith.science/pith/ZNPSAWM53EE5WPUSYPI32TPDSH/action/replication_record"}},"created_at":"2026-07-05T09:40:47.497839+00:00","updated_at":"2026-07-05T09:40:47.497839+00:00"}