{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VRZMCE6WRY4VSM6DRGCDNXNBDP","short_pith_number":"pith:VRZMCE6W","schema_version":"1.0","canonical_sha256":"ac72c113d68e395933c3898436dda11bcb5f5e127ec2a186d1a1ecd793b6fd6b","source":{"kind":"arxiv","id":"2003.06932","version":2},"attestation_state":"computed","paper":{"title":"Self-Constructing Graph Convolutional Networks for Semantic Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnt-B{\\o}rre Salberg, Michael Kampffmeyer, Qinghui Liu, Robert Jenssen","submitted_at":"2020-03-15T21:55:24Z","abstract_excerpt":"Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs. SCG can automatically obtain optimized non-local context graphs from complex-shaped objects in aerial imagery. We optimize SCG via an adaptive d"},"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":"2003.06932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-15T21:55:24Z","cross_cats_sorted":[],"title_canon_sha256":"ec4771a34ca01676249fa8589dc4f3f987631a7a63abd510889a19af6713a6fa","abstract_canon_sha256":"a15edb2d0c3ac58521f46a2bb142744d4eb38338d3dc418fa93fd25d8d4f8092"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:44.636626Z","signature_b64":"iVSf/dXvd4vwFEHWRc1GKSE1rSSyAFtcavgymlkhI8q1Tzx8CQBdufRhW03XPzr6FJcF7SHUwfa350gi1zRHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac72c113d68e395933c3898436dda11bcb5f5e127ec2a186d1a1ecd793b6fd6b","last_reissued_at":"2026-07-05T00:57:44.636205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:44.636205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Constructing Graph Convolutional Networks for Semantic Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnt-B{\\o}rre Salberg, Michael Kampffmeyer, Qinghui Liu, Robert Jenssen","submitted_at":"2020-03-15T21:55:24Z","abstract_excerpt":"Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs. SCG can automatically obtain optimized non-local context graphs from complex-shaped objects in aerial imagery. We optimize SCG via an adaptive d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06932","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/2003.06932/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":"2003.06932","created_at":"2026-07-05T00:57:44.636259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06932v2","created_at":"2026-07-05T00:57:44.636259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06932","created_at":"2026-07-05T00:57:44.636259+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRZMCE6WRY4V","created_at":"2026-07-05T00:57:44.636259+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRZMCE6WRY4VSM6D","created_at":"2026-07-05T00:57:44.636259+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRZMCE6W","created_at":"2026-07-05T00:57:44.636259+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/VRZMCE6WRY4VSM6DRGCDNXNBDP","json":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP.json","graph_json":"https://pith.science/api/pith-number/VRZMCE6WRY4VSM6DRGCDNXNBDP/graph.json","events_json":"https://pith.science/api/pith-number/VRZMCE6WRY4VSM6DRGCDNXNBDP/events.json","paper":"https://pith.science/paper/VRZMCE6W"},"agent_actions":{"view_html":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP","download_json":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP.json","view_paper":"https://pith.science/paper/VRZMCE6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06932&json=true","fetch_graph":"https://pith.science/api/pith-number/VRZMCE6WRY4VSM6DRGCDNXNBDP/graph.json","fetch_events":"https://pith.science/api/pith-number/VRZMCE6WRY4VSM6DRGCDNXNBDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP/action/storage_attestation","attest_author":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP/action/author_attestation","sign_citation":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP/action/citation_signature","submit_replication":"https://pith.science/pith/VRZMCE6WRY4VSM6DRGCDNXNBDP/action/replication_record"}},"created_at":"2026-07-05T00:57:44.636259+00:00","updated_at":"2026-07-05T00:57:44.636259+00:00"}