{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R3UB6EELLTWM2W2MAFXRJPLMIO","short_pith_number":"pith:R3UB6EEL","schema_version":"1.0","canonical_sha256":"8ee81f108b5ceccd5b4c016f14bd6c43a6b278034980b92575e6340bb288dbc3","source":{"kind":"arxiv","id":"1912.01756","version":4},"attestation_state":"computed","paper":{"title":"Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuyang Zhang, Nelson Nauata, Yasutaka Furukawa","submitted_at":"2019-12-04T01:15:51Z","abstract_excerpt":"This paper proposes a novel message passing neural (MPN) architecture Conv-MPN, which reconstructs an outdoor building as a planar graph from a single RGB image. Conv-MPN is specifically designed for cases where nodes of a graph have explicit spatial embedding. In our problem, nodes correspond to building edges in an image. Conv-MPN is different from MPN in that 1) the feature associated with a node is represented as a feature volume instead of a 1D vector; and 2) convolutions encode messages instead of fully connected layers. Conv-MPN learns to select a true subset of nodes (i.e., building ed"},"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":"1912.01756","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T01:15:51Z","cross_cats_sorted":[],"title_canon_sha256":"1b582ba7b40ff2063067ac66e69d84db291a71665e2d12ff2146774a498c7e7e","abstract_canon_sha256":"63a7679313e90227d9824d31803487ec49d1279b38e5bf9c826e95aa94a6c7ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:39.995483Z","signature_b64":"0QNeSUxYsPMYNHkFZoQrLsr60wb+xLphku5TWCMSjRjwrDIduAAcE1SKDbAQ9zMxF2H3yGVS70kqAhyZILNjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ee81f108b5ceccd5b4c016f14bd6c43a6b278034980b92575e6340bb288dbc3","last_reissued_at":"2026-07-05T02:46:39.995081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:39.995081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuyang Zhang, Nelson Nauata, Yasutaka Furukawa","submitted_at":"2019-12-04T01:15:51Z","abstract_excerpt":"This paper proposes a novel message passing neural (MPN) architecture Conv-MPN, which reconstructs an outdoor building as a planar graph from a single RGB image. Conv-MPN is specifically designed for cases where nodes of a graph have explicit spatial embedding. In our problem, nodes correspond to building edges in an image. Conv-MPN is different from MPN in that 1) the feature associated with a node is represented as a feature volume instead of a 1D vector; and 2) convolutions encode messages instead of fully connected layers. Conv-MPN learns to select a true subset of nodes (i.e., building ed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01756","kind":"arxiv","version":4},"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/1912.01756/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":"1912.01756","created_at":"2026-07-05T02:46:39.995138+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.01756v4","created_at":"2026-07-05T02:46:39.995138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01756","created_at":"2026-07-05T02:46:39.995138+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3UB6EELLTWM","created_at":"2026-07-05T02:46:39.995138+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3UB6EELLTWM2W2M","created_at":"2026-07-05T02:46:39.995138+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3UB6EEL","created_at":"2026-07-05T02:46:39.995138+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/R3UB6EELLTWM2W2MAFXRJPLMIO","json":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO.json","graph_json":"https://pith.science/api/pith-number/R3UB6EELLTWM2W2MAFXRJPLMIO/graph.json","events_json":"https://pith.science/api/pith-number/R3UB6EELLTWM2W2MAFXRJPLMIO/events.json","paper":"https://pith.science/paper/R3UB6EEL"},"agent_actions":{"view_html":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO","download_json":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO.json","view_paper":"https://pith.science/paper/R3UB6EEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.01756&json=true","fetch_graph":"https://pith.science/api/pith-number/R3UB6EELLTWM2W2MAFXRJPLMIO/graph.json","fetch_events":"https://pith.science/api/pith-number/R3UB6EELLTWM2W2MAFXRJPLMIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO/action/storage_attestation","attest_author":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO/action/author_attestation","sign_citation":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO/action/citation_signature","submit_replication":"https://pith.science/pith/R3UB6EELLTWM2W2MAFXRJPLMIO/action/replication_record"}},"created_at":"2026-07-05T02:46:39.995138+00:00","updated_at":"2026-07-05T02:46:39.995138+00:00"}