{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IY5NMA7FWETV5D27WH5FFJFXK5","short_pith_number":"pith:IY5NMA7F","schema_version":"1.0","canonical_sha256":"463ad603e5b1275e8f5fb1fa52a4b757488b412a107901472c84525525776685","source":{"kind":"arxiv","id":"2301.04612","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Wu, Julius Pfrommer, J\\\"urgen Beyerer, Mingyuan Zhou","submitted_at":"2023-01-11T18:14:24Z","abstract_excerpt":"We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying shape. The main idea is to combine a contrastive loss between the resulting latent representations with an additional reconstruction loss. That helps to avoid collapsing the latent representations as a trivial solution for minimizing the contrastive loss. A novel dynamic switching approach is used to cross-train two encoders with a shared decoder. The switching "},"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":"2301.04612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-11T18:14:24Z","cross_cats_sorted":[],"title_canon_sha256":"059570e7174c2c867fdcb5ea285d22ee8465ec69ee1656374a47ac865f8c8dc2","abstract_canon_sha256":"78ac6075a7ea22a6c3ce290073f693b7fa13f4a245610bf901bf227bae480909"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:47.078510Z","signature_b64":"hcnQb8pdVLamgjOaA2PGDna3cS10GVUpjcS6A7MPuaQnf60qv3hEB4EJfoLtwmSBOkjZC83rgPXBpvhOyNRtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"463ad603e5b1275e8f5fb1fa52a4b757488b412a107901472c84525525776685","last_reissued_at":"2026-07-05T11:16:47.077995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:47.077995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Wu, Julius Pfrommer, J\\\"urgen Beyerer, Mingyuan Zhou","submitted_at":"2023-01-11T18:14:24Z","abstract_excerpt":"We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying shape. The main idea is to combine a contrastive loss between the resulting latent representations with an additional reconstruction loss. That helps to avoid collapsing the latent representations as a trivial solution for minimizing the contrastive loss. A novel dynamic switching approach is used to cross-train two encoders with a shared decoder. The switching "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04612","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/2301.04612/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":"2301.04612","created_at":"2026-07-05T11:16:47.078056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04612v2","created_at":"2026-07-05T11:16:47.078056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04612","created_at":"2026-07-05T11:16:47.078056+00:00"},{"alias_kind":"pith_short_12","alias_value":"IY5NMA7FWETV","created_at":"2026-07-05T11:16:47.078056+00:00"},{"alias_kind":"pith_short_16","alias_value":"IY5NMA7FWETV5D27","created_at":"2026-07-05T11:16:47.078056+00:00"},{"alias_kind":"pith_short_8","alias_value":"IY5NMA7F","created_at":"2026-07-05T11:16:47.078056+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/IY5NMA7FWETV5D27WH5FFJFXK5","json":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5.json","graph_json":"https://pith.science/api/pith-number/IY5NMA7FWETV5D27WH5FFJFXK5/graph.json","events_json":"https://pith.science/api/pith-number/IY5NMA7FWETV5D27WH5FFJFXK5/events.json","paper":"https://pith.science/paper/IY5NMA7F"},"agent_actions":{"view_html":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5","download_json":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5.json","view_paper":"https://pith.science/paper/IY5NMA7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04612&json=true","fetch_graph":"https://pith.science/api/pith-number/IY5NMA7FWETV5D27WH5FFJFXK5/graph.json","fetch_events":"https://pith.science/api/pith-number/IY5NMA7FWETV5D27WH5FFJFXK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5/action/storage_attestation","attest_author":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5/action/author_attestation","sign_citation":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5/action/citation_signature","submit_replication":"https://pith.science/pith/IY5NMA7FWETV5D27WH5FFJFXK5/action/replication_record"}},"created_at":"2026-07-05T11:16:47.078056+00:00","updated_at":"2026-07-05T11:16:47.078056+00:00"}