{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3NX7PZZ37QWEAZA7T7K5DUOA6V","short_pith_number":"pith:3NX7PZZ3","canonical_record":{"source":{"id":"2605.01799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:39:44Z","cross_cats_sorted":[],"title_canon_sha256":"cdbca880381d1320937de09d4b42f0559f17bafc491d6523c558391a6c0c9539","abstract_canon_sha256":"2e885fb1490a17be734ef89a18f37e499987734288aa1e80346ba549aaf97df7"},"schema_version":"1.0"},"canonical_sha256":"db6ff7e73bfc2c40641f9fd5d1d1c0f568d01ff9608988690552bc8ac812e2e4","source":{"kind":"arxiv","id":"2605.01799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01799","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01799v2","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01799","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"3NX7PZZ37QWE","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"3NX7PZZ37QWEAZA7","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"3NX7PZZ3","created_at":"2026-06-09T01:05:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3NX7PZZ37QWEAZA7T7K5DUOA6V","target":"record","payload":{"canonical_record":{"source":{"id":"2605.01799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:39:44Z","cross_cats_sorted":[],"title_canon_sha256":"cdbca880381d1320937de09d4b42f0559f17bafc491d6523c558391a6c0c9539","abstract_canon_sha256":"2e885fb1490a17be734ef89a18f37e499987734288aa1e80346ba549aaf97df7"},"schema_version":"1.0"},"canonical_sha256":"db6ff7e73bfc2c40641f9fd5d1d1c0f568d01ff9608988690552bc8ac812e2e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:18.612090Z","signature_b64":"0ERyeNtCRmUcZzBOYqiVFJLWhhF1T3zvemQD92Jhk6tyfkXrWEuGG4DMilNd16Ywd7Qmzkzijn+vjalmNWZ5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db6ff7e73bfc2c40641f9fd5d1d1c0f568d01ff9608988690552bc8ac812e2e4","last_reissued_at":"2026-06-09T01:05:18.611675Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:18.611675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.01799","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":"2026-06-09T01:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQGE2gNRwtYh0ig1GS2p157FVVym6WjNVRkUHrk41GwbVzzUs6eomvsZFIKrkizs/T7eye58lGDtldh4rtrNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:07:38.965911Z"},"content_sha256":"c67832b1d5b17f62681fe81504e324d7dfa3303a84d49d4699aa6943c1e6454f","schema_version":"1.0","event_id":"sha256:c67832b1d5b17f62681fe81504e324d7dfa3303a84d49d4699aa6943c1e6454f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3NX7PZZ37QWEAZA7T7K5DUOA6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Embody4D generates consistent 4D videos of robot actions from single-camera footage.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Hanxin Zhu, Jiayi Luo, Jingwen Sun, Peiyan Tu, Shaojie Ren, Xiaoqian Cheng, Yuyan Xu, Zhibo Chen","submitted_at":"2026-05-03T09:39:44Z","abstract_excerpt":"Embodied agents require robust and comprehensive 3D spatiotemporal representations to support spatial reasoning, manipulation understanding, and downstream decision making. However, existing robot data are typically captured from fixed or sparse viewpoints, providing only partial and view-dependent observations, which limits multi-view perception and generalization across viewpoints. Given the difficulty of collecting additional viewpoints in real-world settings, we propose Embody4D, a dedicated video-to-video world model for embodied scenarios to bridge this observation gap by transforming a "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Embody4D achieves state-of-the-art performance, serving as a robust world model that synthesizes high-fidelity, view-consistent videos to empower downstream robotic planning and learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 3D-aware compositional synthesis pipeline, adaptive noise injection strategy, and interaction-aware attention mechanism together solve data scarcity, spatiotemporal inconsistency, and manipulation hallucination without new failure modes or overfitting to the curated dataset.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Embody4D generates consistent 4D videos of robot actions from single-camera footage.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bc4883a5dd5204d4cd3bc12196a607395b6556bd4279da50b72b4381b03f69e4"},"source":{"id":"2605.01799","kind":"arxiv","version":2},"verdict":{"id":"57e5d43b-917a-41ad-ae0d-27513788b545","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T19:11:50.092971Z","strongest_claim":"Embody4D achieves state-of-the-art performance, serving as a robust world model that synthesizes high-fidelity, view-consistent videos to empower downstream robotic planning and learning.","one_line_summary":"Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 3D-aware compositional synthesis pipeline, adaptive noise injection strategy, and interaction-aware attention mechanism together solve data scarcity, spatiotemporal inconsistency, and manipulation hallucination without new failure modes or overfitting to the curated dataset.","pith_extraction_headline":"Embody4D generates consistent 4D videos of robot actions from single-camera footage."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01799/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:35:51.892882Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:22.671228Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:58:08.646730Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d54fc7a738a937743d29dcf3d8554fde04d9099bc56d7c747ee98a4bf84a5189"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9a5dbb69af6b2d4ea2b609e4c9ff75eb73f3f7d61e062e43cb8a2cf93bc57cf4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"57e5d43b-917a-41ad-ae0d-27513788b545"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQFQkI8JqHBqcs8s9uFAzLpWy+EzilNlQUrrtU0+7hPeOtgOwhqySCy5BqmNVyjqbaTWaitVrfRjPURpyRnhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:07:38.966749Z"},"content_sha256":"a8aaebfcc899b133a2bb5bd741d2d579fd80c10e0a1535da75b9a969af718d79","schema_version":"1.0","event_id":"sha256:a8aaebfcc899b133a2bb5bd741d2d579fd80c10e0a1535da75b9a969af718d79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V/bundle.json","state_url":"https://pith.science/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V/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":"2026-08-20T21:07:38Z","links":{"resolver":"https://pith.science/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V","bundle":"https://pith.science/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V/bundle.json","state":"https://pith.science/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NX7PZZ37QWEAZA7T7K5DUOA6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3NX7PZZ37QWEAZA7T7K5DUOA6V","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":"2e885fb1490a17be734ef89a18f37e499987734288aa1e80346ba549aaf97df7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:39:44Z","title_canon_sha256":"cdbca880381d1320937de09d4b42f0559f17bafc491d6523c558391a6c0c9539"},"schema_version":"1.0","source":{"id":"2605.01799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01799","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01799v2","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01799","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"3NX7PZZ37QWE","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"3NX7PZZ37QWEAZA7","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"3NX7PZZ3","created_at":"2026-06-09T01:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:a8aaebfcc899b133a2bb5bd741d2d579fd80c10e0a1535da75b9a969af718d79","target":"graph","created_at":"2026-06-09T01:05:18Z","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":"Embody4D achieves state-of-the-art performance, serving as a robust world model that synthesizes high-fidelity, view-consistent videos to empower downstream robotic planning and learning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 3D-aware compositional synthesis pipeline, adaptive noise injection strategy, and interaction-aware attention mechanism together solve data scarcity, spatiotemporal inconsistency, and manipulation hallucination without new failure modes or overfitting to the curated dataset."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Embody4D generates consistent 4D videos of robot actions from single-camera footage."}],"snapshot_sha256":"bc4883a5dd5204d4cd3bc12196a607395b6556bd4279da50b72b4381b03f69e4"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9a5dbb69af6b2d4ea2b609e4c9ff75eb73f3f7d61e062e43cb8a2cf93bc57cf4"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T17:35:51.892882Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:22.671228Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:58:08.646730Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01799/integrity.json","findings":[],"snapshot_sha256":"d54fc7a738a937743d29dcf3d8554fde04d9099bc56d7c747ee98a4bf84a5189","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied agents require robust and comprehensive 3D spatiotemporal representations to support spatial reasoning, manipulation understanding, and downstream decision making. However, existing robot data are typically captured from fixed or sparse viewpoints, providing only partial and view-dependent observations, which limits multi-view perception and generalization across viewpoints. Given the difficulty of collecting additional viewpoints in real-world settings, we propose Embody4D, a dedicated video-to-video world model for embodied scenarios to bridge this observation gap by transforming a ","authors_text":"Cong Wang, Hanxin Zhu, Jiayi Luo, Jingwen Sun, Peiyan Tu, Shaojie Ren, Xiaoqian Cheng, Yuyan Xu, Zhibo Chen","cross_cats":[],"headline":"Embody4D generates consistent 4D videos of robot actions from single-camera footage.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:39:44Z","title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01799","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T19:11:50.092971Z","id":"57e5d43b-917a-41ad-ae0d-27513788b545","model_set":{"reader":"grok-4.3"},"one_line_summary":"Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Embody4D generates consistent 4D videos of robot actions from single-camera footage.","strongest_claim":"Embody4D achieves state-of-the-art performance, serving as a robust world model that synthesizes high-fidelity, view-consistent videos to empower downstream robotic planning and learning.","weakest_assumption":"That the 3D-aware compositional synthesis pipeline, adaptive noise injection strategy, and interaction-aware attention mechanism together solve data scarcity, spatiotemporal inconsistency, and manipulation hallucination without new failure modes or overfitting to the curated dataset."}},"verdict_id":"57e5d43b-917a-41ad-ae0d-27513788b545"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c67832b1d5b17f62681fe81504e324d7dfa3303a84d49d4699aa6943c1e6454f","target":"record","created_at":"2026-06-09T01:05:18Z","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":"2e885fb1490a17be734ef89a18f37e499987734288aa1e80346ba549aaf97df7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:39:44Z","title_canon_sha256":"cdbca880381d1320937de09d4b42f0559f17bafc491d6523c558391a6c0c9539"},"schema_version":"1.0","source":{"id":"2605.01799","kind":"arxiv","version":2}},"canonical_sha256":"db6ff7e73bfc2c40641f9fd5d1d1c0f568d01ff9608988690552bc8ac812e2e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db6ff7e73bfc2c40641f9fd5d1d1c0f568d01ff9608988690552bc8ac812e2e4","first_computed_at":"2026-06-09T01:05:18.611675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:18.611675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ERyeNtCRmUcZzBOYqiVFJLWhhF1T3zvemQD92Jhk6tyfkXrWEuGG4DMilNd16Ywd7Qmzkzijn+vjalmNWZ5Bw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:18.612090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c67832b1d5b17f62681fe81504e324d7dfa3303a84d49d4699aa6943c1e6454f","sha256:a8aaebfcc899b133a2bb5bd741d2d579fd80c10e0a1535da75b9a969af718d79"],"state_sha256":"8ffa3f7892372b1fda5ac4b5ced3017175ec4b7388d13132bfe36eceaf9296ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JS+Xl2RtT2K5EjDrgkQEMRMacC8k+4zbfsnp7Qvg/ZmuCF93mvBQgFcddNfsMjrnyzp5a+klam9kl83IUdSBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:07:38.975212Z","bundle_sha256":"8718551560492a16ba9ac826af0ec1e008816d8118db214d1fe1a2308de4f2a7"}}