{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MP6FU326VBDGX32HHBOHPAIXRM","short_pith_number":"pith:MP6FU326","schema_version":"1.0","canonical_sha256":"63fc5a6f5ea8466bef47385c7781178b004f1858942226b3426bfb1442c12182","source":{"kind":"arxiv","id":"2508.17230","version":2},"attestation_state":"computed","paper":{"title":"4D Visual Pre-training for Robot Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengkai Hou, Huazhe Xu, Shanghang Zhang, Songbo Hu, Yanjie Ze, Yankai Fu, Yue Yu, Zeyu Gao","submitted_at":"2025-08-24T07:06:56Z","abstract_excerpt":"General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D images, neglecting the inherent 3D nature of the world. However, due to the scarcity of large-scale 3D data, it is still hard to extract a universal 3D representation from web datasets. Instead, we are seeking a general visual pre-training framework that could improve all 3D representations as an alternative. Our framework, called FVP, is a novel 4D Visual Pre"},"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":"2508.17230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T07:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"7a7ea5eb6a95e659ab09377e2f9f4885953fa72e5fee6a96edb17cc59139c747","abstract_canon_sha256":"324685a0b90331e0dfb5102a217dbe569e6bd4641c5e691bd85a1cf18a5239e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:18.540517Z","signature_b64":"T5Ca9gQbIO9ZbjzCIPJAm31zzM/W0wwKXX8gehNATRH09BSdl663gsSu7kT1nAAS51Ioh5mHRNOpHCNAKuD6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63fc5a6f5ea8466bef47385c7781178b004f1858942226b3426bfb1442c12182","last_reissued_at":"2026-07-05T12:06:18.540039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:18.540039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"4D Visual Pre-training for Robot Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengkai Hou, Huazhe Xu, Shanghang Zhang, Songbo Hu, Yanjie Ze, Yankai Fu, Yue Yu, Zeyu Gao","submitted_at":"2025-08-24T07:06:56Z","abstract_excerpt":"General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D images, neglecting the inherent 3D nature of the world. However, due to the scarcity of large-scale 3D data, it is still hard to extract a universal 3D representation from web datasets. Instead, we are seeking a general visual pre-training framework that could improve all 3D representations as an alternative. Our framework, called FVP, is a novel 4D Visual Pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17230","kind":"arxiv","version":2},"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/2508.17230/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":"2508.17230","created_at":"2026-07-05T12:06:18.540090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17230v2","created_at":"2026-07-05T12:06:18.540090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17230","created_at":"2026-07-05T12:06:18.540090+00:00"},{"alias_kind":"pith_short_12","alias_value":"MP6FU326VBDG","created_at":"2026-07-05T12:06:18.540090+00:00"},{"alias_kind":"pith_short_16","alias_value":"MP6FU326VBDGX32H","created_at":"2026-07-05T12:06:18.540090+00:00"},{"alias_kind":"pith_short_8","alias_value":"MP6FU326","created_at":"2026-07-05T12:06:18.540090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28215","citing_title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM","json":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM.json","graph_json":"https://pith.science/api/pith-number/MP6FU326VBDGX32HHBOHPAIXRM/graph.json","events_json":"https://pith.science/api/pith-number/MP6FU326VBDGX32HHBOHPAIXRM/events.json","paper":"https://pith.science/paper/MP6FU326"},"agent_actions":{"view_html":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM","download_json":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM.json","view_paper":"https://pith.science/paper/MP6FU326","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17230&json=true","fetch_graph":"https://pith.science/api/pith-number/MP6FU326VBDGX32HHBOHPAIXRM/graph.json","fetch_events":"https://pith.science/api/pith-number/MP6FU326VBDGX32HHBOHPAIXRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM/action/storage_attestation","attest_author":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM/action/author_attestation","sign_citation":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM/action/citation_signature","submit_replication":"https://pith.science/pith/MP6FU326VBDGX32HHBOHPAIXRM/action/replication_record"}},"created_at":"2026-07-05T12:06:18.540090+00:00","updated_at":"2026-07-05T12:06:18.540090+00:00"}