{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CEUKALJH4S6TOVPXY46EILCH7C","short_pith_number":"pith:CEUKALJH","schema_version":"1.0","canonical_sha256":"1128a02d27e4bd3755f7c73c442c47f8ae84dca918db5f8d2c44057798851b09","source":{"kind":"arxiv","id":"2606.26410","version":1},"attestation_state":"computed","paper":{"title":"Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Niloy Mitra, Zican Wang","submitted_at":"2026-06-24T22:06:35Z","abstract_excerpt":"We present a self-supervised framework for learning implicit 3D physical dynamics directly from video-derived supervisory signals. While current generative video models achieve high visual fidelity, they lack a 3D geometric foundation, often resulting in physical inconsistencies and a failure to maintain object permanence. We address this by shifting the predictive bottleneck from 2D image space to a `lifted' 3D Volumetric Latent Space. Our method unprojects semantic features from a Video Joint-Embedding Predictive Architecture (V-JEPA) into a voxelized grid, grounded by monocular depth priors"},"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":"2606.26410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T22:06:35Z","cross_cats_sorted":[],"title_canon_sha256":"0657d62cc5dd49087dd67c42e2be52070112541221abd086967fc795083b98f3","abstract_canon_sha256":"49c440e9701aee5bc9d7cf3d8a81524b8e3531eae9488f2a9aa88faac0c4b73d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:40.202523Z","signature_b64":"p9baKEe6TdvvlIdzs1RSheraMpWuyV3AgAr5RCuzztdjdGgAqKJKN9AfjdkUW7oxJiUxlagSalc2PhJ0sGj2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1128a02d27e4bd3755f7c73c442c47f8ae84dca918db5f8d2c44057798851b09","last_reissued_at":"2026-06-26T00:15:40.202124Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:40.202124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Niloy Mitra, Zican Wang","submitted_at":"2026-06-24T22:06:35Z","abstract_excerpt":"We present a self-supervised framework for learning implicit 3D physical dynamics directly from video-derived supervisory signals. While current generative video models achieve high visual fidelity, they lack a 3D geometric foundation, often resulting in physical inconsistencies and a failure to maintain object permanence. We address this by shifting the predictive bottleneck from 2D image space to a `lifted' 3D Volumetric Latent Space. Our method unprojects semantic features from a Video Joint-Embedding Predictive Architecture (V-JEPA) into a voxelized grid, grounded by monocular depth priors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26410","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/2606.26410/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":"2606.26410","created_at":"2026-06-26T00:15:40.202180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26410v1","created_at":"2026-06-26T00:15:40.202180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26410","created_at":"2026-06-26T00:15:40.202180+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEUKALJH4S6T","created_at":"2026-06-26T00:15:40.202180+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEUKALJH4S6TOVPX","created_at":"2026-06-26T00:15:40.202180+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEUKALJH","created_at":"2026-06-26T00:15:40.202180+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/CEUKALJH4S6TOVPXY46EILCH7C","json":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C.json","graph_json":"https://pith.science/api/pith-number/CEUKALJH4S6TOVPXY46EILCH7C/graph.json","events_json":"https://pith.science/api/pith-number/CEUKALJH4S6TOVPXY46EILCH7C/events.json","paper":"https://pith.science/paper/CEUKALJH"},"agent_actions":{"view_html":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C","download_json":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C.json","view_paper":"https://pith.science/paper/CEUKALJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26410&json=true","fetch_graph":"https://pith.science/api/pith-number/CEUKALJH4S6TOVPXY46EILCH7C/graph.json","fetch_events":"https://pith.science/api/pith-number/CEUKALJH4S6TOVPXY46EILCH7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C/action/storage_attestation","attest_author":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C/action/author_attestation","sign_citation":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C/action/citation_signature","submit_replication":"https://pith.science/pith/CEUKALJH4S6TOVPXY46EILCH7C/action/replication_record"}},"created_at":"2026-06-26T00:15:40.202180+00:00","updated_at":"2026-06-26T00:15:40.202180+00:00"}