{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2YYPRK74AIHACSGU3IEE27YV47","short_pith_number":"pith:2YYPRK74","schema_version":"1.0","canonical_sha256":"d630f8abfc020e0148d4da084d7f15e7f025f3767c1b2ba1ad7b3d9dd4cb899e","source":{"kind":"arxiv","id":"2205.02904","version":1},"attestation_state":"computed","paper":{"title":"Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Jun Saito, Kunal Gupta, Noam Aigerman, Siddhartha Chaudhuri, Thibault Groueix, Vladimir G. Kim","submitted_at":"2022-05-05T19:51:13Z","abstract_excerpt":"This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art. The framework is based on reducing the neural aspect to a prediction of a matrix for a single given point, conditioned on a global shape descriptor. The field of matrices is then projected onto the tangent bundle of the given mesh, and used as candidate jaco"},"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":"2205.02904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GR","submitted_at":"2022-05-05T19:51:13Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"4c4f103836e1c58ae6754127a0eb5de086c36a1abd31db66b932b21cc201bc96","abstract_canon_sha256":"8e06cc0dd09f95b43a78ccfff03716508c469a43af1ba27f639256c9422ac684"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:46.162728Z","signature_b64":"w86b2T5QiOXW57qXfSUimnJswi9hUS9UHk7jWmIFcbss3aqwTwQdUhcwkG1Q7XEZ92JZnjwiT95JdbK8ugCpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d630f8abfc020e0148d4da084d7f15e7f025f3767c1b2ba1ad7b3d9dd4cb899e","last_reissued_at":"2026-07-05T04:20:46.162305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:46.162305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Jun Saito, Kunal Gupta, Noam Aigerman, Siddhartha Chaudhuri, Thibault Groueix, Vladimir G. Kim","submitted_at":"2022-05-05T19:51:13Z","abstract_excerpt":"This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art. The framework is based on reducing the neural aspect to a prediction of a matrix for a single given point, conditioned on a global shape descriptor. The field of matrices is then projected onto the tangent bundle of the given mesh, and used as candidate jaco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02904","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/2205.02904/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":"2205.02904","created_at":"2026-07-05T04:20:46.162368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02904v1","created_at":"2026-07-05T04:20:46.162368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02904","created_at":"2026-07-05T04:20:46.162368+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YYPRK74AIHA","created_at":"2026-07-05T04:20:46.162368+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YYPRK74AIHACSGU","created_at":"2026-07-05T04:20:46.162368+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YYPRK74","created_at":"2026-07-05T04:20:46.162368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18039","citing_title":"SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08799","citing_title":"MeshOn: Intersection-Free Mesh-to-Mesh Composition","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47","json":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47.json","graph_json":"https://pith.science/api/pith-number/2YYPRK74AIHACSGU3IEE27YV47/graph.json","events_json":"https://pith.science/api/pith-number/2YYPRK74AIHACSGU3IEE27YV47/events.json","paper":"https://pith.science/paper/2YYPRK74"},"agent_actions":{"view_html":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47","download_json":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47.json","view_paper":"https://pith.science/paper/2YYPRK74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02904&json=true","fetch_graph":"https://pith.science/api/pith-number/2YYPRK74AIHACSGU3IEE27YV47/graph.json","fetch_events":"https://pith.science/api/pith-number/2YYPRK74AIHACSGU3IEE27YV47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47/action/storage_attestation","attest_author":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47/action/author_attestation","sign_citation":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47/action/citation_signature","submit_replication":"https://pith.science/pith/2YYPRK74AIHACSGU3IEE27YV47/action/replication_record"}},"created_at":"2026-07-05T04:20:46.162368+00:00","updated_at":"2026-07-05T04:20:46.162368+00:00"}