{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UIAHKDXEK2PGBKT3QIQQPABW7R","short_pith_number":"pith:UIAHKDXE","canonical_record":{"source":{"id":"2510.17568","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T14:17:16Z","cross_cats_sorted":[],"title_canon_sha256":"6d99c90d1854192118f664d9f4820e86f619902fa33dc52671aa2fc7081598ea","abstract_canon_sha256":"b908cdf08f0d4e54d5b2110fab3572b57a28fd18f904c49658eb6d1b66ac969c"},"schema_version":"1.0"},"canonical_sha256":"a200750ee4569e60aa7b8221078036fc59d45ce637e4b35ff95789996c56e789","source":{"kind":"arxiv","id":"2510.17568","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.17568","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2510.17568v7","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17568","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"UIAHKDXEK2PG","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"UIAHKDXEK2PGBKT3","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"UIAHKDXE","created_at":"2026-06-08T01:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UIAHKDXEK2PGBKT3QIQQPABW7R","target":"record","payload":{"canonical_record":{"source":{"id":"2510.17568","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T14:17:16Z","cross_cats_sorted":[],"title_canon_sha256":"6d99c90d1854192118f664d9f4820e86f619902fa33dc52671aa2fc7081598ea","abstract_canon_sha256":"b908cdf08f0d4e54d5b2110fab3572b57a28fd18f904c49658eb6d1b66ac969c"},"schema_version":"1.0"},"canonical_sha256":"a200750ee4569e60aa7b8221078036fc59d45ce637e4b35ff95789996c56e789","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:03.457011Z","signature_b64":"Ck5zywnjlOQ5Qd9/7B4PADxbsmsA7kHYaW1qK+jLsnyleYGX3E0nbWfmpTWOJM4npjKqXbXA+30tMIWsJuTWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a200750ee4569e60aa7b8221078036fc59d45ce637e4b35ff95789996c56e789","last_reissued_at":"2026-06-08T01:05:03.456068Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:03.456068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.17568","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vs41haBARv8iEsQZdke3fXOWBkUsUbvVnKbH2lPPrtZjwfKOPy/I4tbJzfke/lOMHJVkkJq9mpUfv5DAEx8/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:01:11.847103Z"},"content_sha256":"5b49d4599e04f006b0b1860dfa17e533e5ffbcb341e75c0e7b4a15b07b8fcead","schema_version":"1.0","event_id":"sha256:5b49d4599e04f006b0b1860dfa17e533e5ffbcb341e75c0e7b4a15b07b8fcead"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UIAHKDXEK2PGBKT3QIQQPABW7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PAGE-4D extends VGGT to dynamic scenes by using a dynamics-aware mask to disentangle pose and geometry estimation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangneng Zhan, Gaspard Beaudouin, Grace Chen, Kaichen Zhou, Mengyu Wang, Paul Pu Liang, Xinhai Chang, Yuhan Wang","submitted_at":"2025-10-20T14:17:16Z","abstract_excerpt":"Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction and point cloud reconstruction - all without post-processing. A central"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a single predicted dynamics-aware mask can reliably suppress motion cues for pose estimation while amplifying them for geometry reconstruction without creating new inconsistencies or requiring heavy task-specific fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PAGE-4D is a feedforward extension of VGGT that uses a dynamics-aware aggregator and mask to disentangle pose estimation from geometry reconstruction in videos with moving objects.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PAGE-4D extends VGGT to dynamic scenes by using a dynamics-aware mask to disentangle pose and geometry estimation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"34092d4b163cf490ea147eb9f1f5322d800e46681df84eb4bd412c80e3027577"},"source":{"id":"2510.17568","kind":"arxiv","version":7},"verdict":{"id":"0cbb19a0-d588-4994-80ef-d7d531c557d8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T06:16:20.846753Z","strongest_claim":"PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction.","one_line_summary":"PAGE-4D is a feedforward extension of VGGT that uses a dynamics-aware aggregator and mask to disentangle pose estimation from geometry reconstruction in videos with moving objects.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a single predicted dynamics-aware mask can reliably suppress motion cues for pose estimation while amplifying them for geometry reconstruction without creating new inconsistencies or requiring heavy task-specific fine-tuning.","pith_extraction_headline":"PAGE-4D extends VGGT to dynamic scenes by using a dynamics-aware mask to disentangle pose and geometry estimation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.17568/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":2,"snapshot_sha256":"e92ced43a91c658ad8c51b8456d573bdddba3b91f3846621e1820bbe3962f720"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0cbb19a0-d588-4994-80ef-d7d531c557d8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VFSaRNspC463jWipqsBHpUK/5vvSjFKc4DMqipk16OrNXFMjtqTAgjULZzMPfPnb5Zy9A8wgyxYOzc06rrZaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:01:11.847544Z"},"content_sha256":"0a14b5eb5edac0d4de0ad64cda83675b7b253f15870fb0494f56868825aa96f5","schema_version":"1.0","event_id":"sha256:0a14b5eb5edac0d4de0ad64cda83675b7b253f15870fb0494f56868825aa96f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UIAHKDXEK2PGBKT3QIQQPABW7R/bundle.json","state_url":"https://pith.science/pith/UIAHKDXEK2PGBKT3QIQQPABW7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UIAHKDXEK2PGBKT3QIQQPABW7R/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":"2026-08-19T09:01:11Z","links":{"resolver":"https://pith.science/pith/UIAHKDXEK2PGBKT3QIQQPABW7R","bundle":"https://pith.science/pith/UIAHKDXEK2PGBKT3QIQQPABW7R/bundle.json","state":"https://pith.science/pith/UIAHKDXEK2PGBKT3QIQQPABW7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UIAHKDXEK2PGBKT3QIQQPABW7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UIAHKDXEK2PGBKT3QIQQPABW7R","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":"b908cdf08f0d4e54d5b2110fab3572b57a28fd18f904c49658eb6d1b66ac969c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T14:17:16Z","title_canon_sha256":"6d99c90d1854192118f664d9f4820e86f619902fa33dc52671aa2fc7081598ea"},"schema_version":"1.0","source":{"id":"2510.17568","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.17568","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2510.17568v7","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17568","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"UIAHKDXEK2PG","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"UIAHKDXEK2PGBKT3","created_at":"2026-06-08T01:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"UIAHKDXE","created_at":"2026-06-08T01:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:0a14b5eb5edac0d4de0ad64cda83675b7b253f15870fb0494f56868825aa96f5","target":"graph","created_at":"2026-06-08T01:05:03Z","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":"PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single predicted dynamics-aware mask can reliably suppress motion cues for pose estimation while amplifying them for geometry reconstruction without creating new inconsistencies or requiring heavy task-specific fine-tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PAGE-4D is a feedforward extension of VGGT that uses a dynamics-aware aggregator and mask to disentangle pose estimation from geometry reconstruction in videos with moving objects."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PAGE-4D extends VGGT to dynamic scenes by using a dynamics-aware mask to disentangle pose and geometry estimation."}],"snapshot_sha256":"34092d4b163cf490ea147eb9f1f5322d800e46681df84eb4bd412c80e3027577"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e92ced43a91c658ad8c51b8456d573bdddba3b91f3846621e1820bbe3962f720"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.17568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction and point cloud reconstruction - all without post-processing. A central","authors_text":"Fangneng Zhan, Gaspard Beaudouin, Grace Chen, Kaichen Zhou, Mengyu Wang, Paul Pu Liang, Xinhai Chang, Yuhan Wang","cross_cats":[],"headline":"PAGE-4D extends VGGT to dynamic scenes by using a dynamics-aware mask to disentangle pose and geometry estimation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T14:17:16Z","title":"PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.17568","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-18T06:16:20.846753Z","id":"0cbb19a0-d588-4994-80ef-d7d531c557d8","model_set":{"reader":"grok-4.3"},"one_line_summary":"PAGE-4D is a feedforward extension of VGGT that uses a dynamics-aware aggregator and mask to disentangle pose estimation from geometry reconstruction in videos with moving objects.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PAGE-4D extends VGGT to dynamic scenes by using a dynamics-aware mask to disentangle pose and geometry estimation.","strongest_claim":"PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction.","weakest_assumption":"That a single predicted dynamics-aware mask can reliably suppress motion cues for pose estimation while amplifying them for geometry reconstruction without creating new inconsistencies or requiring heavy task-specific fine-tuning."}},"verdict_id":"0cbb19a0-d588-4994-80ef-d7d531c557d8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b49d4599e04f006b0b1860dfa17e533e5ffbcb341e75c0e7b4a15b07b8fcead","target":"record","created_at":"2026-06-08T01:05:03Z","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":"b908cdf08f0d4e54d5b2110fab3572b57a28fd18f904c49658eb6d1b66ac969c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T14:17:16Z","title_canon_sha256":"6d99c90d1854192118f664d9f4820e86f619902fa33dc52671aa2fc7081598ea"},"schema_version":"1.0","source":{"id":"2510.17568","kind":"arxiv","version":7}},"canonical_sha256":"a200750ee4569e60aa7b8221078036fc59d45ce637e4b35ff95789996c56e789","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a200750ee4569e60aa7b8221078036fc59d45ce637e4b35ff95789996c56e789","first_computed_at":"2026-06-08T01:05:03.456068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:03.456068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ck5zywnjlOQ5Qd9/7B4PADxbsmsA7kHYaW1qK+jLsnyleYGX3E0nbWfmpTWOJM4npjKqXbXA+30tMIWsJuTWAg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:03.457011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.17568","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b49d4599e04f006b0b1860dfa17e533e5ffbcb341e75c0e7b4a15b07b8fcead","sha256:0a14b5eb5edac0d4de0ad64cda83675b7b253f15870fb0494f56868825aa96f5"],"state_sha256":"21ef3addb96e81fdacccc381703ccc80636710dff564128584ff32a47ab278e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bQWMRzA76VdOr3TYLDOAJWW/QB9NahTl9HJL7U43N0q2mjtBbw0S0kSCRnGJyzeDSOXIm072S9apKrpnAkeCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:01:11.850888Z","bundle_sha256":"02a95fedd25761d4f93092d9f20b922031cd42a878c7f52322c7705854efe638"}}