{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7PHGZIQMWJR2R2CEZXBX3DMNOU","short_pith_number":"pith:7PHGZIQM","schema_version":"1.0","canonical_sha256":"fbce6ca20cb263a8e844cdc37d8d8d752e302eff73acc441d015d1c43125f7e2","source":{"kind":"arxiv","id":"2403.16051","version":3},"attestation_state":"computed","paper":{"title":"Segment Anything Model for Road Network Graph Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cindy Le, Congrui Hetang, Haoru Xue, Tianwei Yue, Wenping Wang, Yihui He","submitted_at":"2024-03-24T07:36:38Z","abstract_excerpt":"We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry, we formulate it as a dense semantic segmentation task, leveraging the inherent strengths of SAM. The image encoder of SAM is fine-tuned to produce probability masks for roads and intersections, from which the graph vertices are extracted via simple non-maximum suppression. To predict graph topology, we designed a lightweight transformer-based graph neural network, which leverages the SAM image embeddings to estimate"},"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":"2403.16051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T07:36:38Z","cross_cats_sorted":[],"title_canon_sha256":"0ea2e596bb29084544471aa91eeefb1372da5037217ffe8aa33a1e8447d357dc","abstract_canon_sha256":"4e884ee2bfc196d2412db746b7cc02d8d91555c309facab5390a0de844a63cdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:34.865845Z","signature_b64":"P//plB7tZmEQeQindU3sTb6IOOWmbctRTMGubOuwmdTRQzEbx+Kj+Akp0PfZOM31LrTxRx8dBvvho9xc4qO+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbce6ca20cb263a8e844cdc37d8d8d752e302eff73acc441d015d1c43125f7e2","last_reissued_at":"2026-07-05T08:07:34.861669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:34.861669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Anything Model for Road Network Graph Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cindy Le, Congrui Hetang, Haoru Xue, Tianwei Yue, Wenping Wang, Yihui He","submitted_at":"2024-03-24T07:36:38Z","abstract_excerpt":"We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry, we formulate it as a dense semantic segmentation task, leveraging the inherent strengths of SAM. The image encoder of SAM is fine-tuned to produce probability masks for roads and intersections, from which the graph vertices are extracted via simple non-maximum suppression. To predict graph topology, we designed a lightweight transformer-based graph neural network, which leverages the SAM image embeddings to estimate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16051","kind":"arxiv","version":3},"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/2403.16051/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":"2403.16051","created_at":"2026-07-05T08:07:34.861728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16051v3","created_at":"2026-07-05T08:07:34.861728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16051","created_at":"2026-07-05T08:07:34.861728+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PHGZIQMWJR2","created_at":"2026-07-05T08:07:34.861728+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PHGZIQMWJR2R2CE","created_at":"2026-07-05T08:07:34.861728+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PHGZIQM","created_at":"2026-07-05T08:07:34.861728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07496","citing_title":"PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07496","citing_title":"PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU","json":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU.json","graph_json":"https://pith.science/api/pith-number/7PHGZIQMWJR2R2CEZXBX3DMNOU/graph.json","events_json":"https://pith.science/api/pith-number/7PHGZIQMWJR2R2CEZXBX3DMNOU/events.json","paper":"https://pith.science/paper/7PHGZIQM"},"agent_actions":{"view_html":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU","download_json":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU.json","view_paper":"https://pith.science/paper/7PHGZIQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16051&json=true","fetch_graph":"https://pith.science/api/pith-number/7PHGZIQMWJR2R2CEZXBX3DMNOU/graph.json","fetch_events":"https://pith.science/api/pith-number/7PHGZIQMWJR2R2CEZXBX3DMNOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU/action/storage_attestation","attest_author":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU/action/author_attestation","sign_citation":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU/action/citation_signature","submit_replication":"https://pith.science/pith/7PHGZIQMWJR2R2CEZXBX3DMNOU/action/replication_record"}},"created_at":"2026-07-05T08:07:34.861728+00:00","updated_at":"2026-07-05T08:07:34.861728+00:00"}