{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HL2AJVZVG6OORA63STT5TZ5UEN","short_pith_number":"pith:HL2AJVZV","canonical_record":{"source":{"id":"2605.09989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:06:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"67f9e5b3eb95d7e01569922077eb53cfa87efbc6b9f444eec2efd75d0abc716a","abstract_canon_sha256":"c60fb6f557a94350ec4b26b7ef8e9910b19e778df40055bdb126efb04363960a"},"schema_version":"1.0"},"canonical_sha256":"3af404d735379ce883db94e7d9e7b42377d1d1ac629ee2781ed8937fc82437ce","source":{"kind":"arxiv","id":"2605.09989","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09989","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09989v2","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09989","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"HL2AJVZVG6OO","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"HL2AJVZVG6OORA63","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"HL2AJVZV","created_at":"2026-06-05T00:13:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HL2AJVZVG6OORA63STT5TZ5UEN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.09989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:06:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"67f9e5b3eb95d7e01569922077eb53cfa87efbc6b9f444eec2efd75d0abc716a","abstract_canon_sha256":"c60fb6f557a94350ec4b26b7ef8e9910b19e778df40055bdb126efb04363960a"},"schema_version":"1.0"},"canonical_sha256":"3af404d735379ce883db94e7d9e7b42377d1d1ac629ee2781ed8937fc82437ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:46.928547Z","signature_b64":"7+V1jkTbwluiQEpQyp8wD2h8+P/Df7rYNsQRdUrahYNMjXMgvGIWKhRP1mJkAPDzVJWa72gFyTYYhUFvxBM3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3af404d735379ce883db94e7d9e7b42377d1d1ac629ee2781ed8937fc82437ce","last_reissued_at":"2026-06-05T00:13:46.928048Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:46.928048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.09989","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7cl/H1H4QNv31gq9gnMqXV6JzT5DDJLh+vbWvBe0Xx1hGe3Uzd2obmkj5BDMoDmiGGjmUjSdqUV3QR8P9RGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:58.909680Z"},"content_sha256":"39acb15d5ba3b7513da7b60692f0e783ba16751a6fb955d74525541df3169512","schema_version":"1.0","event_id":"sha256:39acb15d5ba3b7513da7b60692f0e783ba16751a6fb955d74525541df3169512"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HL2AJVZVG6OORA63STT5TZ5UEN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"StereoPolicy processes synchronized stereo image pairs with 2D encoders and a fusion transformer to improve robotic manipulation policies without explicit 3D reconstruction.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Evans Han, Haoyue Xiao, Huang Huang, Jiajun Wu, Jianwen Xie, Li Fei-Fei, Ruohan Zhang, Yingke Wang, Yunfan Jiang","submitted_at":"2026-05-11T05:06:12Z","abstract_excerpt":"Recent advances in robot imitation learning have produced powerful visuomotor policies that manipulate diverse objects from visual inputs. However, monocular observations lack depth information, which is critical for precise manipulation in cluttered or geometrically complex scenes. Explicit depth maps and point clouds are often noisy and fragile in real-world manipulation. We introduce StereoPolicy, a visuomotor policy learning framework that directly leverages synchronized stereo image pairs to improve geometric reasoning without constructing explicit 3D representations. StereoPolicy process"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"StereoPolicy delivers consistent improvements over RGB, RGB-D, point cloud, and multi-view baselines across three simulation benchmarks (RoboMimic, RoboCasa, OmniGibson) and is validated on real-robot tabletop and bimanual mobile manipulation tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That processing each stereo image independently with pretrained 2D encoders and fusing via a Stereo Transformer is sufficient to implicitly capture spatial correspondence and disparity cues without explicit 3D reconstruction or camera calibration.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations and real-robot tests.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"StereoPolicy processes synchronized stereo image pairs with 2D encoders and a fusion transformer to improve robotic manipulation policies without explicit 3D reconstruction.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"103802e8a85e8009eadc6e4f1687beac9f84e6f7ebcd7bbdbf91558249ba9da3"},"source":{"id":"2605.09989","kind":"arxiv","version":2},"verdict":{"id":"cbcc4303-5c84-4c35-8c8f-44556d6d2365","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T03:52:55.765366Z","strongest_claim":"StereoPolicy delivers consistent improvements over RGB, RGB-D, point cloud, and multi-view baselines across three simulation benchmarks (RoboMimic, RoboCasa, OmniGibson) and is validated on real-robot tabletop and bimanual mobile manipulation tasks.","one_line_summary":"StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations and real-robot tests.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That processing each stereo image independently with pretrained 2D encoders and fusing via a Stereo Transformer is sufficient to implicitly capture spatial correspondence and disparity cues without explicit 3D reconstruction or camera calibration.","pith_extraction_headline":"StereoPolicy processes synchronized stereo image pairs with 2D encoders and a fusion transformer to improve robotic manipulation policies without explicit 3D reconstruction."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09989/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:42:01.139588Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:42:59.280084Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:18.274443Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:47:36.361058Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3af1d0facaa0c510fe9e407955f7a82c4b4d32d984263b8df746104a03d153ce"},"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"},"verdict_id":"cbcc4303-5c84-4c35-8c8f-44556d6d2365"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TpjZyxGdWbmCRnEAcwbceQF3HpqvabBg6Il+G2adz62ofNggAGSE2JA610s/zIvxE2KWqC/MJ2Lt9QZy0sCLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:58.910475Z"},"content_sha256":"e4e1680999a1552612ad7a76fee46ba0b15f0d4421be01fecc8ef72b961929ba","schema_version":"1.0","event_id":"sha256:e4e1680999a1552612ad7a76fee46ba0b15f0d4421be01fecc8ef72b961929ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HL2AJVZVG6OORA63STT5TZ5UEN/bundle.json","state_url":"https://pith.science/pith/HL2AJVZVG6OORA63STT5TZ5UEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HL2AJVZVG6OORA63STT5TZ5UEN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T18:51:58Z","links":{"resolver":"https://pith.science/pith/HL2AJVZVG6OORA63STT5TZ5UEN","bundle":"https://pith.science/pith/HL2AJVZVG6OORA63STT5TZ5UEN/bundle.json","state":"https://pith.science/pith/HL2AJVZVG6OORA63STT5TZ5UEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HL2AJVZVG6OORA63STT5TZ5UEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HL2AJVZVG6OORA63STT5TZ5UEN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c60fb6f557a94350ec4b26b7ef8e9910b19e778df40055bdb126efb04363960a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:06:12Z","title_canon_sha256":"67f9e5b3eb95d7e01569922077eb53cfa87efbc6b9f444eec2efd75d0abc716a"},"schema_version":"1.0","source":{"id":"2605.09989","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09989","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09989v2","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09989","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"HL2AJVZVG6OO","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"HL2AJVZVG6OORA63","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"HL2AJVZV","created_at":"2026-06-05T00:13:46Z"}],"graph_snapshots":[{"event_id":"sha256:e4e1680999a1552612ad7a76fee46ba0b15f0d4421be01fecc8ef72b961929ba","target":"graph","created_at":"2026-06-05T00:13:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"StereoPolicy delivers consistent improvements over RGB, RGB-D, point cloud, and multi-view baselines across three simulation benchmarks (RoboMimic, RoboCasa, OmniGibson) and is validated on real-robot tabletop and bimanual mobile manipulation tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That processing each stereo image independently with pretrained 2D encoders and fusing via a Stereo Transformer is sufficient to implicitly capture spatial correspondence and disparity cues without explicit 3D reconstruction or camera calibration."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations and real-robot tests."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"StereoPolicy processes synchronized stereo image pairs with 2D encoders and a fusion transformer to improve robotic manipulation policies without explicit 3D reconstruction."}],"snapshot_sha256":"103802e8a85e8009eadc6e4f1687beac9f84e6f7ebcd7bbdbf91558249ba9da3"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:42:01.139588Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:42:59.280084Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:18.274443Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:47:36.361058Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.09989/integrity.json","findings":[],"snapshot_sha256":"3af1d0facaa0c510fe9e407955f7a82c4b4d32d984263b8df746104a03d153ce","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in robot imitation learning have produced powerful visuomotor policies that manipulate diverse objects from visual inputs. However, monocular observations lack depth information, which is critical for precise manipulation in cluttered or geometrically complex scenes. Explicit depth maps and point clouds are often noisy and fragile in real-world manipulation. We introduce StereoPolicy, a visuomotor policy learning framework that directly leverages synchronized stereo image pairs to improve geometric reasoning without constructing explicit 3D representations. StereoPolicy process","authors_text":"Evans Han, Haoyue Xiao, Huang Huang, Jiajun Wu, Jianwen Xie, Li Fei-Fei, Ruohan Zhang, Yingke Wang, Yunfan Jiang","cross_cats":["cs.CV"],"headline":"StereoPolicy processes synchronized stereo image pairs with 2D encoders and a fusion transformer to improve robotic manipulation policies without explicit 3D reconstruction.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:06:12Z","title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.09989","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T03:52:55.765366Z","id":"cbcc4303-5c84-4c35-8c8f-44556d6d2365","model_set":{"reader":"grok-4.3"},"one_line_summary":"StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations and real-robot tests.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"StereoPolicy processes synchronized stereo image pairs with 2D encoders and a fusion transformer to improve robotic manipulation policies without explicit 3D reconstruction.","strongest_claim":"StereoPolicy delivers consistent improvements over RGB, RGB-D, point cloud, and multi-view baselines across three simulation benchmarks (RoboMimic, RoboCasa, OmniGibson) and is validated on real-robot tabletop and bimanual mobile manipulation tasks.","weakest_assumption":"That processing each stereo image independently with pretrained 2D encoders and fusing via a Stereo Transformer is sufficient to implicitly capture spatial correspondence and disparity cues without explicit 3D reconstruction or camera calibration."}},"verdict_id":"cbcc4303-5c84-4c35-8c8f-44556d6d2365"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39acb15d5ba3b7513da7b60692f0e783ba16751a6fb955d74525541df3169512","target":"record","created_at":"2026-06-05T00:13:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c60fb6f557a94350ec4b26b7ef8e9910b19e778df40055bdb126efb04363960a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:06:12Z","title_canon_sha256":"67f9e5b3eb95d7e01569922077eb53cfa87efbc6b9f444eec2efd75d0abc716a"},"schema_version":"1.0","source":{"id":"2605.09989","kind":"arxiv","version":2}},"canonical_sha256":"3af404d735379ce883db94e7d9e7b42377d1d1ac629ee2781ed8937fc82437ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3af404d735379ce883db94e7d9e7b42377d1d1ac629ee2781ed8937fc82437ce","first_computed_at":"2026-06-05T00:13:46.928048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:46.928048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7+V1jkTbwluiQEpQyp8wD2h8+P/Df7rYNsQRdUrahYNMjXMgvGIWKhRP1mJkAPDzVJWa72gFyTYYhUFvxBM3AA==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:46.928547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.09989","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39acb15d5ba3b7513da7b60692f0e783ba16751a6fb955d74525541df3169512","sha256:e4e1680999a1552612ad7a76fee46ba0b15f0d4421be01fecc8ef72b961929ba"],"state_sha256":"447322e52ea6f4fa37b0389f67b64c4d62c5e2a7b8fd1fbc3d8df52a51da0e2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BOvauNRdV1E0zKudDJjD4eGzoqHV5zKhCa0KNPlGz1KmX2BF9H2HHUmMwpmBXYGnXQYfaP94tUJcabdEnmtCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:51:58.916848Z","bundle_sha256":"dbdfcbae5471816437d05a3f129f66577b236bad7cb2f49e83fabeaa975c54b3"}}