{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YGUK45QVTJ72H2724OTN6S4W5H","short_pith_number":"pith:YGUK45QV","schema_version":"1.0","canonical_sha256":"c1a8ae76159a7fa3ebfae3a6df4b96e9dd7b74b22d6e9e4e96c3da4041f65dca","source":{"kind":"arxiv","id":"1712.08290","version":2},"attestation_state":"computed","paper":{"title":"CSGNet: Neural Shape Parser for Constructive Solid Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Difan Liu, Evangelos Kalogerakis, Gopal Sharma, Rishabh Goyal, Subhransu Maji","submitted_at":"2017-12-22T03:18:57Z","abstract_excerpt":"We present a neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape. The instructions in our program are based on constructive solid geometry principles, i.e., a set of boolean operations on shape primitives defined recursively. Bottom-up techniques for this shape parsing task rely on primitive detection and are inherently slow since the search space over possible primitive combinations is large. In contrast, our model uses a recurrent neural network that parses the input shape in a top-down manner, which is significantly faster and yields a com"},"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":"1712.08290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-22T03:18:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfe0f22a7c2370bf722817acd90a94a9c431b8d373d663b73c2a04a039f5d980","abstract_canon_sha256":"1aa8634efac7b61bfd234373f51770ec5e561055f1da6d935711701bf62e2e8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:41.307599Z","signature_b64":"vV3sknq42Q+rjz/V6+o8cJC0o4n0ItKYm9kh4IsGu5/+jjxDSNKQmN6lkD3N2VnSHVN2eq9tnzAcrXxS/AW7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1a8ae76159a7fa3ebfae3a6df4b96e9dd7b74b22d6e9e4e96c3da4041f65dca","last_reissued_at":"2026-05-18T00:19:41.306872Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:41.306872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSGNet: Neural Shape Parser for Constructive Solid Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Difan Liu, Evangelos Kalogerakis, Gopal Sharma, Rishabh Goyal, Subhransu Maji","submitted_at":"2017-12-22T03:18:57Z","abstract_excerpt":"We present a neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape. The instructions in our program are based on constructive solid geometry principles, i.e., a set of boolean operations on shape primitives defined recursively. Bottom-up techniques for this shape parsing task rely on primitive detection and are inherently slow since the search space over possible primitive combinations is large. In contrast, our model uses a recurrent neural network that parses the input shape in a top-down manner, which is significantly faster and yields a com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08290","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":""},"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":"1712.08290","created_at":"2026-05-18T00:19:41.306985+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.08290v2","created_at":"2026-05-18T00:19:41.306985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08290","created_at":"2026-05-18T00:19:41.306985+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGUK45QVTJ72","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGUK45QVTJ72H272","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGUK45QV","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11680","citing_title":"ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H","json":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H.json","graph_json":"https://pith.science/api/pith-number/YGUK45QVTJ72H2724OTN6S4W5H/graph.json","events_json":"https://pith.science/api/pith-number/YGUK45QVTJ72H2724OTN6S4W5H/events.json","paper":"https://pith.science/paper/YGUK45QV"},"agent_actions":{"view_html":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H","download_json":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H.json","view_paper":"https://pith.science/paper/YGUK45QV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.08290&json=true","fetch_graph":"https://pith.science/api/pith-number/YGUK45QVTJ72H2724OTN6S4W5H/graph.json","fetch_events":"https://pith.science/api/pith-number/YGUK45QVTJ72H2724OTN6S4W5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H/action/storage_attestation","attest_author":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H/action/author_attestation","sign_citation":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H/action/citation_signature","submit_replication":"https://pith.science/pith/YGUK45QVTJ72H2724OTN6S4W5H/action/replication_record"}},"created_at":"2026-05-18T00:19:41.306985+00:00","updated_at":"2026-05-18T00:19:41.306985+00:00"}