{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7MT3HR7B7LJPSJOFQEE4N36TWG","short_pith_number":"pith:7MT3HR7B","schema_version":"1.0","canonical_sha256":"fb27b3c7e1fad2f925c58109c6efd3b1bba651de3f68eb8c6881bf153e3c7aee","source":{"kind":"arxiv","id":"2103.12459","version":2},"attestation_state":"computed","paper":{"title":"Dual Mesh Convolutional Networks for Human Shape Correspondence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adnane Boukhayma, Edmond Boyer, Jakob Verbeek, Nitika Verma","submitted_at":"2021-03-23T11:22:47Z","abstract_excerpt":"Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straight-forward due to their irregular structure. We explore how the dual, face-based representation of triangular meshes can be leveraged as a data structure for graph convolutional networks. In the dual mesh, each node (face) has a fixed number of neighbors, which makes the networks less susceptible to overfitting on the mesh topology, and also al-lows the use of input features that are naturally defined over faces, such as surf"},"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":"2103.12459","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T11:22:47Z","cross_cats_sorted":[],"title_canon_sha256":"b9bde1fe95c192a80936c579554886914e5d30055928e54b2a0c34b65fdab8f7","abstract_canon_sha256":"cbced4af4129b274dc5da07ec903432e0e169810bad39115af8dda7a6bb5bc44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:08.494955Z","signature_b64":"EU61X/XilVC35uj77Yi75oiTkvIlsvA/YnQb4Ve5a6GSjb8WmCHkp0uAc0/4Vq/5QIlVJcCeAazSOfyAe2+pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb27b3c7e1fad2f925c58109c6efd3b1bba651de3f68eb8c6881bf153e3c7aee","last_reissued_at":"2026-07-05T03:23:08.494487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:08.494487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Mesh Convolutional Networks for Human Shape Correspondence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adnane Boukhayma, Edmond Boyer, Jakob Verbeek, Nitika Verma","submitted_at":"2021-03-23T11:22:47Z","abstract_excerpt":"Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straight-forward due to their irregular structure. We explore how the dual, face-based representation of triangular meshes can be leveraged as a data structure for graph convolutional networks. In the dual mesh, each node (face) has a fixed number of neighbors, which makes the networks less susceptible to overfitting on the mesh topology, and also al-lows the use of input features that are naturally defined over faces, such as surf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12459","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/2103.12459/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":"2103.12459","created_at":"2026-07-05T03:23:08.494547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12459v2","created_at":"2026-07-05T03:23:08.494547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12459","created_at":"2026-07-05T03:23:08.494547+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MT3HR7B7LJP","created_at":"2026-07-05T03:23:08.494547+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MT3HR7B7LJPSJOF","created_at":"2026-07-05T03:23:08.494547+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MT3HR7B","created_at":"2026-07-05T03:23:08.494547+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/7MT3HR7B7LJPSJOFQEE4N36TWG","json":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG.json","graph_json":"https://pith.science/api/pith-number/7MT3HR7B7LJPSJOFQEE4N36TWG/graph.json","events_json":"https://pith.science/api/pith-number/7MT3HR7B7LJPSJOFQEE4N36TWG/events.json","paper":"https://pith.science/paper/7MT3HR7B"},"agent_actions":{"view_html":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG","download_json":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG.json","view_paper":"https://pith.science/paper/7MT3HR7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12459&json=true","fetch_graph":"https://pith.science/api/pith-number/7MT3HR7B7LJPSJOFQEE4N36TWG/graph.json","fetch_events":"https://pith.science/api/pith-number/7MT3HR7B7LJPSJOFQEE4N36TWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG/action/storage_attestation","attest_author":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG/action/author_attestation","sign_citation":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG/action/citation_signature","submit_replication":"https://pith.science/pith/7MT3HR7B7LJPSJOFQEE4N36TWG/action/replication_record"}},"created_at":"2026-07-05T03:23:08.494547+00:00","updated_at":"2026-07-05T03:23:08.494547+00:00"}