{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EP67DIMZEBBRFJQCSLVZIIFDOL","short_pith_number":"pith:EP67DIMZ","schema_version":"1.0","canonical_sha256":"23fdf1a199204312a60292eb9420a372c18cfd964ba1c9da3a3755e1932ab4cf","source":{"kind":"arxiv","id":"2607.02707","version":1},"attestation_state":"computed","paper":{"title":"VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Manzanera, David Filliat, Marwane Hariat","submitted_at":"2026-07-02T18:49:34Z","abstract_excerpt":"Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signals. We introduce Vision-Language Reprojection Consistency (VLRC), a scalable auxiliary objective that exploits frozen vision-language representations as semantic multi-view supervision. Given a predicted 3D reconstruction, VLRC reprojects dense vision-language features across views and enforces feature consistency between corresponding image locations, requiring no additional 3D annotations. The objective integrates s"},"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":"2607.02707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T18:49:34Z","cross_cats_sorted":[],"title_canon_sha256":"88da45cfaf6607002814d2c0bcad74b769cbadaed30dc3d5037ae02d5745735c","abstract_canon_sha256":"5c11b7ece01d113248b129f8347f991c2170a404e66306cc26bce617b9ab8136"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:09.829331Z","signature_b64":"ecQiGMZdYcNDE3mxoypkgv8P7VBh7aOxqDj7G+pig9i1c0ipFuEW5qFwAZlCCHyuJ0WzuIoke0TfE9gCg53jAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23fdf1a199204312a60292eb9420a372c18cfd964ba1c9da3a3755e1932ab4cf","last_reissued_at":"2026-07-07T00:16:09.828301Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:09.828301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Manzanera, David Filliat, Marwane Hariat","submitted_at":"2026-07-02T18:49:34Z","abstract_excerpt":"Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signals. We introduce Vision-Language Reprojection Consistency (VLRC), a scalable auxiliary objective that exploits frozen vision-language representations as semantic multi-view supervision. Given a predicted 3D reconstruction, VLRC reprojects dense vision-language features across views and enforces feature consistency between corresponding image locations, requiring no additional 3D annotations. The objective integrates s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02707","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/2607.02707/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":"2607.02707","created_at":"2026-07-07T00:16:09.828436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02707v1","created_at":"2026-07-07T00:16:09.828436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02707","created_at":"2026-07-07T00:16:09.828436+00:00"},{"alias_kind":"pith_short_12","alias_value":"EP67DIMZEBBR","created_at":"2026-07-07T00:16:09.828436+00:00"},{"alias_kind":"pith_short_16","alias_value":"EP67DIMZEBBRFJQC","created_at":"2026-07-07T00:16:09.828436+00:00"},{"alias_kind":"pith_short_8","alias_value":"EP67DIMZ","created_at":"2026-07-07T00:16:09.828436+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/EP67DIMZEBBRFJQCSLVZIIFDOL","json":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL.json","graph_json":"https://pith.science/api/pith-number/EP67DIMZEBBRFJQCSLVZIIFDOL/graph.json","events_json":"https://pith.science/api/pith-number/EP67DIMZEBBRFJQCSLVZIIFDOL/events.json","paper":"https://pith.science/paper/EP67DIMZ"},"agent_actions":{"view_html":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL","download_json":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL.json","view_paper":"https://pith.science/paper/EP67DIMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02707&json=true","fetch_graph":"https://pith.science/api/pith-number/EP67DIMZEBBRFJQCSLVZIIFDOL/graph.json","fetch_events":"https://pith.science/api/pith-number/EP67DIMZEBBRFJQCSLVZIIFDOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL/action/storage_attestation","attest_author":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL/action/author_attestation","sign_citation":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL/action/citation_signature","submit_replication":"https://pith.science/pith/EP67DIMZEBBRFJQCSLVZIIFDOL/action/replication_record"}},"created_at":"2026-07-07T00:16:09.828436+00:00","updated_at":"2026-07-07T00:16:09.828436+00:00"}