{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N4GQVCOUUMD4QRFXE4VLZ6Y4QH","short_pith_number":"pith:N4GQVCOU","schema_version":"1.0","canonical_sha256":"6f0d0a89d4a307c844b7272abcfb1c81deb1b7ee3eec95a21cdb54e2cf1c131a","source":{"kind":"arxiv","id":"2608.05774","version":1},"attestation_state":"computed","paper":{"title":"SR-JEPA: Learning Predictive Latent State in 3D Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Qifu Wen, Xi Zeng, Zihan Zhou","submitted_at":"2026-08-06T09:09:16Z","abstract_excerpt":"Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce. We ask what a trained predictive pathway itself infers when an entire entity is absent from a native 3D scene. We introduce SR-JEPA, a point-native JEPA for scene-scale point clouds whose original frozen predictive pathway can be queried at a supplied location. At evaluation, every point of one object is removed before encoding and replaced by the same shape-free 32-point query at its centroid. Training use"},"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":"2608.05774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T09:09:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f36a344e08b89924326c223965f369801dcdcc76547089cf72c840d5216fde98","abstract_canon_sha256":"fda01c6e0120a8e9ebeb34b017a1782e15e0cb74dce95c8b228360f0e10378b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:43.761315Z","signature_b64":"ypH8+6+jr/zrQuaiCWSTAl1Z8C/OnCvdE8Co28NAQV0kX//M8XxaUAx33wu92rNiUQGRAm5K6Y6KQHGnEwyeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f0d0a89d4a307c844b7272abcfb1c81deb1b7ee3eec95a21cdb54e2cf1c131a","last_reissued_at":"2026-08-07T00:52:43.759974Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:43.759974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SR-JEPA: Learning Predictive Latent State in 3D Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Qifu Wen, Xi Zeng, Zihan Zhou","submitted_at":"2026-08-06T09:09:16Z","abstract_excerpt":"Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce. We ask what a trained predictive pathway itself infers when an entire entity is absent from a native 3D scene. We introduce SR-JEPA, a point-native JEPA for scene-scale point clouds whose original frozen predictive pathway can be queried at a supplied location. At evaluation, every point of one object is removed before encoding and replaced by the same shape-free 32-point query at its centroid. Training use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05774","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/2608.05774/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":"2608.05774","created_at":"2026-08-07T00:52:43.761453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05774v1","created_at":"2026-08-07T00:52:43.761453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05774","created_at":"2026-08-07T00:52:43.761453+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4GQVCOUUMD4","created_at":"2026-08-07T00:52:43.761453+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4GQVCOUUMD4QRFX","created_at":"2026-08-07T00:52:43.761453+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4GQVCOU","created_at":"2026-08-07T00:52:43.761453+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/N4GQVCOUUMD4QRFXE4VLZ6Y4QH","json":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH.json","graph_json":"https://pith.science/api/pith-number/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/graph.json","events_json":"https://pith.science/api/pith-number/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/events.json","paper":"https://pith.science/paper/N4GQVCOU"},"agent_actions":{"view_html":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH","download_json":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH.json","view_paper":"https://pith.science/paper/N4GQVCOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05774&json=true","fetch_graph":"https://pith.science/api/pith-number/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/graph.json","fetch_events":"https://pith.science/api/pith-number/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/action/storage_attestation","attest_author":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/action/author_attestation","sign_citation":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/action/citation_signature","submit_replication":"https://pith.science/pith/N4GQVCOUUMD4QRFXE4VLZ6Y4QH/action/replication_record"}},"created_at":"2026-08-07T00:52:43.761453+00:00","updated_at":"2026-08-07T00:52:43.761453+00:00"}