{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VXSJCQ3QXTO7SMCRHH3AFKQ6DE","short_pith_number":"pith:VXSJCQ3Q","schema_version":"1.0","canonical_sha256":"ade4914370bcddf9305139f602aa1e1910b43a4cd7eb92f9ff8287c15d265d64","source":{"kind":"arxiv","id":"2506.07865","version":1},"attestation_state":"computed","paper":{"title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bo Yang, Jinxi Li, Siyuan Zhou, Ziyang Song","submitted_at":"2025-06-09T15:31:25Z","abstract_excerpt":"In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos. By applying various governing PDEs as PINN losses or incorporating physics simulation into neural networks, existing works often fail to learn complex physical motions at boundaries or require object priors such as masks or types. In this paper, we propose FreeGave to learn the physics of complex dynamic 3D scenes without needing any object priors. The key to our approach is to introduce a physics code followed by a carefully designed divergence-free module for estimating a p"},"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":"2506.07865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:31:25Z","cross_cats_sorted":["cs.AI","cs.CE","cs.LG","cs.RO"],"title_canon_sha256":"cbce35c5ce8af614b307c4c43b06142289828a12a35ac115b53d961c0b1265b0","abstract_canon_sha256":"fdd06e83242d456202d24603e14f84a61332f5325a913b8e2e4ff79ff7c09ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:34.662597Z","signature_b64":"ZL0wJZvnCGmxaSLfEY5GSMY1s5qL4BfsYtMdKUqU3TPEfoHKx3hdbdXEt1XeDSGHK4vA4V0Kd2XHz2bwVTYdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ade4914370bcddf9305139f602aa1e1910b43a4cd7eb92f9ff8287c15d265d64","last_reissued_at":"2026-07-05T11:18:34.662096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:34.662096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bo Yang, Jinxi Li, Siyuan Zhou, Ziyang Song","submitted_at":"2025-06-09T15:31:25Z","abstract_excerpt":"In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos. By applying various governing PDEs as PINN losses or incorporating physics simulation into neural networks, existing works often fail to learn complex physical motions at boundaries or require object priors such as masks or types. In this paper, we propose FreeGave to learn the physics of complex dynamic 3D scenes without needing any object priors. The key to our approach is to introduce a physics code followed by a carefully designed divergence-free module for estimating a p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07865","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/2506.07865/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":"2506.07865","created_at":"2026-07-05T11:18:34.662155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07865v1","created_at":"2026-07-05T11:18:34.662155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07865","created_at":"2026-07-05T11:18:34.662155+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXSJCQ3QXTO7","created_at":"2026-07-05T11:18:34.662155+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXSJCQ3QXTO7SMCR","created_at":"2026-07-05T11:18:34.662155+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXSJCQ3Q","created_at":"2026-07-05T11:18:34.662155+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/VXSJCQ3QXTO7SMCRHH3AFKQ6DE","json":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE.json","graph_json":"https://pith.science/api/pith-number/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/graph.json","events_json":"https://pith.science/api/pith-number/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/events.json","paper":"https://pith.science/paper/VXSJCQ3Q"},"agent_actions":{"view_html":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE","download_json":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE.json","view_paper":"https://pith.science/paper/VXSJCQ3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07865&json=true","fetch_graph":"https://pith.science/api/pith-number/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/graph.json","fetch_events":"https://pith.science/api/pith-number/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/action/storage_attestation","attest_author":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/action/author_attestation","sign_citation":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/action/citation_signature","submit_replication":"https://pith.science/pith/VXSJCQ3QXTO7SMCRHH3AFKQ6DE/action/replication_record"}},"created_at":"2026-07-05T11:18:34.662155+00:00","updated_at":"2026-07-05T11:18:34.662155+00:00"}