{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5H7RRXDRZPXFLBJLB5LDU2IJ3W","short_pith_number":"pith:5H7RRXDR","canonical_record":{"source":{"id":"1711.03129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-08T19:29:01Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"5bc34a72aa5c0eb85ebb39b1282c013210515f743e13a8867a874c91301f5d92","abstract_canon_sha256":"108583e36e510fae18d5dab160791df8e9cfcae88fa372f3ac40cad836a4b029"},"schema_version":"1.0"},"canonical_sha256":"e9ff18dc71cbee55852b0f563a6909dda09b4ddb831fa674584e6a4d57c82869","source":{"kind":"arxiv","id":"1711.03129","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.03129","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"1711.03129v1","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03129","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"5H7RRXDRZPXF","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5H7RRXDRZPXFLBJL","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5H7RRXDR","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5H7RRXDRZPXFLBJLB5LDU2IJ3W","target":"record","payload":{"canonical_record":{"source":{"id":"1711.03129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-08T19:29:01Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"5bc34a72aa5c0eb85ebb39b1282c013210515f743e13a8867a874c91301f5d92","abstract_canon_sha256":"108583e36e510fae18d5dab160791df8e9cfcae88fa372f3ac40cad836a4b029"},"schema_version":"1.0"},"canonical_sha256":"e9ff18dc71cbee55852b0f563a6909dda09b4ddb831fa674584e6a4d57c82869","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:57.062812Z","signature_b64":"p4WMyPwqrpBcMrCCRiWd1xtR3rU0KlyACzNFw+8bSbSmxv6+a514ZZn61dqGYFiKEVZLms5re0ljEhH2/pD5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ff18dc71cbee55852b0f563a6909dda09b4ddb831fa674584e6a4d57c82869","last_reissued_at":"2026-05-18T00:30:57.062204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:57.062204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.03129","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAmiKGhb5cJIgj/HN+bAZxYE8MYz9n3Y0rWckFXrPCf6dEojAs/qhrBkh2Y++XjYYA34x/f1L9xBKQgm31nSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:06:13.120867Z"},"content_sha256":"e8465c95a97773998c2dfe1f694592c044c346b0f01dc4bb69f4743fbaf68aa4","schema_version":"1.0","event_id":"sha256:e8465c95a97773998c2dfe1f694592c044c346b0f01dc4bb69f4743fbaf68aa4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5H7RRXDRZPXFLBJLB5LDU2IJ3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Joshua B Tenenbaum, Tianfan Xue, William T Freeman, Xingyuan Sun, Yifan Wang","submitted_at":"2017-11-08T19:29:01Z","abstract_excerpt":"3D object reconstruction from a single image is a highly under-determined problem, requiring strong prior knowledge of plausible 3D shapes. This introduces challenges for learning-based approaches, as 3D object annotations are scarce in real images. Previous work chose to train on synthetic data with ground truth 3D information, but suffered from domain adaptation when tested on real data. In this work, we propose MarrNet, an end-to-end trainable model that sequentially estimates 2.5D sketches and 3D object shape. Our disentangled, two-step formulation has three advantages. First, compared to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03129","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8s/oWjvRCQ/xzCif9Nw+zuDUadziKr+9PExLviEAh49O3z7NykfUDnm4x1iIzNU1MSJyasu2PpjtiT3ItuwOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:06:13.121726Z"},"content_sha256":"2b83ed0b7d6f64c30c2c7c016e2d35e1c20022fa94d624648cde6e1be1a98097","schema_version":"1.0","event_id":"sha256:2b83ed0b7d6f64c30c2c7c016e2d35e1c20022fa94d624648cde6e1be1a98097"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W/bundle.json","state_url":"https://pith.science/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T21:06:13Z","links":{"resolver":"https://pith.science/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W","bundle":"https://pith.science/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W/bundle.json","state":"https://pith.science/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5H7RRXDRZPXFLBJLB5LDU2IJ3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5H7RRXDRZPXFLBJLB5LDU2IJ3W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"108583e36e510fae18d5dab160791df8e9cfcae88fa372f3ac40cad836a4b029","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-08T19:29:01Z","title_canon_sha256":"5bc34a72aa5c0eb85ebb39b1282c013210515f743e13a8867a874c91301f5d92"},"schema_version":"1.0","source":{"id":"1711.03129","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.03129","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"1711.03129v1","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03129","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"5H7RRXDRZPXF","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5H7RRXDRZPXFLBJL","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5H7RRXDR","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:2b83ed0b7d6f64c30c2c7c016e2d35e1c20022fa94d624648cde6e1be1a98097","target":"graph","created_at":"2026-05-18T00:30:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"3D object reconstruction from a single image is a highly under-determined problem, requiring strong prior knowledge of plausible 3D shapes. This introduces challenges for learning-based approaches, as 3D object annotations are scarce in real images. Previous work chose to train on synthetic data with ground truth 3D information, but suffered from domain adaptation when tested on real data. In this work, we propose MarrNet, an end-to-end trainable model that sequentially estimates 2.5D sketches and 3D object shape. Our disentangled, two-step formulation has three advantages. First, compared to ","authors_text":"Jiajun Wu, Joshua B Tenenbaum, Tianfan Xue, William T Freeman, Xingyuan Sun, Yifan Wang","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-08T19:29:01Z","title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03129","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e8465c95a97773998c2dfe1f694592c044c346b0f01dc4bb69f4743fbaf68aa4","target":"record","created_at":"2026-05-18T00:30:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"108583e36e510fae18d5dab160791df8e9cfcae88fa372f3ac40cad836a4b029","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-08T19:29:01Z","title_canon_sha256":"5bc34a72aa5c0eb85ebb39b1282c013210515f743e13a8867a874c91301f5d92"},"schema_version":"1.0","source":{"id":"1711.03129","kind":"arxiv","version":1}},"canonical_sha256":"e9ff18dc71cbee55852b0f563a6909dda09b4ddb831fa674584e6a4d57c82869","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9ff18dc71cbee55852b0f563a6909dda09b4ddb831fa674584e6a4d57c82869","first_computed_at":"2026-05-18T00:30:57.062204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:57.062204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p4WMyPwqrpBcMrCCRiWd1xtR3rU0KlyACzNFw+8bSbSmxv6+a514ZZn61dqGYFiKEVZLms5re0ljEhH2/pD5Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:57.062812Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.03129","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8465c95a97773998c2dfe1f694592c044c346b0f01dc4bb69f4743fbaf68aa4","sha256:2b83ed0b7d6f64c30c2c7c016e2d35e1c20022fa94d624648cde6e1be1a98097"],"state_sha256":"c86b233751f078a452f97fc125fff0ef971baee666e6fafdf1494a30cc671d2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i30+IXa49loX4YYGFPdI9WPyRCwxurH4RTFq0HMb724ikoFzMLQYCRGtKRcT05pMSUEOv4VszDU32gjr9CrZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:06:13.126838Z","bundle_sha256":"9f3ffe03bcc56c56bcab8e25a1fbdf3da2729011c9e8eae0982fd2fee70615d6"}}