{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D7IUU6QL6CYBPJ4IPR4F5OTORW","short_pith_number":"pith:D7IUU6QL","schema_version":"1.0","canonical_sha256":"1fd14a7a0bf0b017a7887c785eba6e8d983a03a3c62ea03740065c6251d504c3","source":{"kind":"arxiv","id":"2506.18683","version":1},"attestation_state":"computed","paper":{"title":"SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds from RGB Images for 2D Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Edi Prifti, Eric Chenin, Hanane Ariouat, Jean-Daniel Zucker, Youcef Sklab","submitted_at":"2025-06-23T14:25:40Z","abstract_excerpt":"We introduce the Shape-Image Multimodal Network (SIM-Net), a novel 2D image classification architecture that integrates 3D point cloud representations inferred directly from RGB images. Our key contribution lies in a pixel-to-point transformation that converts 2D object masks into 3D point clouds, enabling the fusion of texture-based and geometric features for enhanced classification performance. SIM-Net is particularly well-suited for the classification of digitized herbarium specimens (a task made challenging by heterogeneous backgrounds), non-plant elements, and occlusions that compromise c"},"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":"2506.18683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T14:25:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75fca71bc55afaa592175d74289f0d8a76e0079e051cf67e4488415ec30d965e","abstract_canon_sha256":"ac024f1057c0a67c5ea31741074f18473e8cface04c5660327dea303e238e20b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:54.116743Z","signature_b64":"0o+yRf77TqZK17q+BEbduO8JGXC/TBAoJCHN7I8QnI8Dnev2wph7QyHGRNDE0P6vgfG6gcVfNz2iAU9n36jZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fd14a7a0bf0b017a7887c785eba6e8d983a03a3c62ea03740065c6251d504c3","last_reissued_at":"2026-07-05T11:25:54.116253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:54.116253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds from RGB Images for 2D Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Edi Prifti, Eric Chenin, Hanane Ariouat, Jean-Daniel Zucker, Youcef Sklab","submitted_at":"2025-06-23T14:25:40Z","abstract_excerpt":"We introduce the Shape-Image Multimodal Network (SIM-Net), a novel 2D image classification architecture that integrates 3D point cloud representations inferred directly from RGB images. Our key contribution lies in a pixel-to-point transformation that converts 2D object masks into 3D point clouds, enabling the fusion of texture-based and geometric features for enhanced classification performance. SIM-Net is particularly well-suited for the classification of digitized herbarium specimens (a task made challenging by heterogeneous backgrounds), non-plant elements, and occlusions that compromise c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18683","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/2506.18683/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":"2506.18683","created_at":"2026-07-05T11:25:54.116313+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18683v1","created_at":"2026-07-05T11:25:54.116313+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18683","created_at":"2026-07-05T11:25:54.116313+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7IUU6QL6CYB","created_at":"2026-07-05T11:25:54.116313+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7IUU6QL6CYBPJ4I","created_at":"2026-07-05T11:25:54.116313+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7IUU6QL","created_at":"2026-07-05T11:25:54.116313+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/D7IUU6QL6CYBPJ4IPR4F5OTORW","json":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW.json","graph_json":"https://pith.science/api/pith-number/D7IUU6QL6CYBPJ4IPR4F5OTORW/graph.json","events_json":"https://pith.science/api/pith-number/D7IUU6QL6CYBPJ4IPR4F5OTORW/events.json","paper":"https://pith.science/paper/D7IUU6QL"},"agent_actions":{"view_html":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW","download_json":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW.json","view_paper":"https://pith.science/paper/D7IUU6QL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18683&json=true","fetch_graph":"https://pith.science/api/pith-number/D7IUU6QL6CYBPJ4IPR4F5OTORW/graph.json","fetch_events":"https://pith.science/api/pith-number/D7IUU6QL6CYBPJ4IPR4F5OTORW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW/action/storage_attestation","attest_author":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW/action/author_attestation","sign_citation":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW/action/citation_signature","submit_replication":"https://pith.science/pith/D7IUU6QL6CYBPJ4IPR4F5OTORW/action/replication_record"}},"created_at":"2026-07-05T11:25:54.116313+00:00","updated_at":"2026-07-05T11:25:54.116313+00:00"}