{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GI2ZQEKGW3UUOMZYU7FYHRFNLD","short_pith_number":"pith:GI2ZQEKG","schema_version":"1.0","canonical_sha256":"3235981146b6e9473338a7cb83c4ad58cc2cb30ef25f4ffdb6354449146bcbd1","source":{"kind":"arxiv","id":"2409.15803","version":1},"attestation_state":"computed","paper":{"title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhe Cheng, Jihua Zhu, Naiwen Hu, Shiqi Li, Yifan Xie","submitted_at":"2024-09-24T06:53:59Z","abstract_excerpt":"Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable to all downstream tasks, and the latter indiscriminately reconstructs masked regions, resulting in irrelevant details being saved in the representation space. To solve the problem above, we introduce 3D-JEPA, a novel non-generative 3D SSRL framework. Specifically, we propose a multi-block sampling strategy that produces a sufficiently informative context bl"},"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":"2409.15803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T06:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"9377af980897f3d9c10871f60906f0056b614f7b10f4a518fe8ecdc081759665","abstract_canon_sha256":"67351559d52caf2c7b89d0e12ad358e50fc21de47d8dbbfe3905ed5434e969bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:00.527078Z","signature_b64":"oQSpivepFAAKNhneYpyN5KzF0nH+6qUV/dQE41nPQlX3M8hH5fRN/LWFSETpt8jswVXSUorLqa5RdiZycfYEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3235981146b6e9473338a7cb83c4ad58cc2cb30ef25f4ffdb6354449146bcbd1","last_reissued_at":"2026-07-05T09:11:00.526579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:00.526579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhe Cheng, Jihua Zhu, Naiwen Hu, Shiqi Li, Yifan Xie","submitted_at":"2024-09-24T06:53:59Z","abstract_excerpt":"Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable to all downstream tasks, and the latter indiscriminately reconstructs masked regions, resulting in irrelevant details being saved in the representation space. To solve the problem above, we introduce 3D-JEPA, a novel non-generative 3D SSRL framework. Specifically, we propose a multi-block sampling strategy that produces a sufficiently informative context bl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15803","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/2409.15803/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":"2409.15803","created_at":"2026-07-05T09:11:00.526640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15803v1","created_at":"2026-07-05T09:11:00.526640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15803","created_at":"2026-07-05T09:11:00.526640+00:00"},{"alias_kind":"pith_short_12","alias_value":"GI2ZQEKGW3UU","created_at":"2026-07-05T09:11:00.526640+00:00"},{"alias_kind":"pith_short_16","alias_value":"GI2ZQEKGW3UUOMZY","created_at":"2026-07-05T09:11:00.526640+00:00"},{"alias_kind":"pith_short_8","alias_value":"GI2ZQEKG","created_at":"2026-07-05T09:11:00.526640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26410","citing_title":"Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01520","citing_title":"TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05586","citing_title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD","json":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD.json","graph_json":"https://pith.science/api/pith-number/GI2ZQEKGW3UUOMZYU7FYHRFNLD/graph.json","events_json":"https://pith.science/api/pith-number/GI2ZQEKGW3UUOMZYU7FYHRFNLD/events.json","paper":"https://pith.science/paper/GI2ZQEKG"},"agent_actions":{"view_html":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD","download_json":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD.json","view_paper":"https://pith.science/paper/GI2ZQEKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15803&json=true","fetch_graph":"https://pith.science/api/pith-number/GI2ZQEKGW3UUOMZYU7FYHRFNLD/graph.json","fetch_events":"https://pith.science/api/pith-number/GI2ZQEKGW3UUOMZYU7FYHRFNLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD/action/storage_attestation","attest_author":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD/action/author_attestation","sign_citation":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD/action/citation_signature","submit_replication":"https://pith.science/pith/GI2ZQEKGW3UUOMZYU7FYHRFNLD/action/replication_record"}},"created_at":"2026-07-05T09:11:00.526640+00:00","updated_at":"2026-07-05T09:11:00.526640+00:00"}