{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TL36UPZBZJ7YXWSD373SZC3GUG","short_pith_number":"pith:TL36UPZB","schema_version":"1.0","canonical_sha256":"9af7ea3f21ca7f8bda43dff72c8b66a1b51405e1a299665e848ba2bd7eaa10cc","source":{"kind":"arxiv","id":"2503.20199","version":1},"attestation_state":"computed","paper":{"title":"Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arthur Ouaknine, David Rolnick, Etienne Lalibert\\'e, Hugo Larochelle, M\\'elisande Teng, Yoshua Bengio","submitted_at":"2025-03-26T03:45:36Z","abstract_excerpt":"The potential of tree planting as a natural climate solution is often undermined by inadequate monitoring of tree planting projects. Current monitoring methods involve measuring trees by hand for each species, requiring extensive cost, time, and labour. Advances in drone remote sensing and computer vision offer great potential for mapping and characterizing trees from aerial imagery, and large pre-trained vision models, such as the Segment Anything Model (SAM), may be a particularly compelling choice given limited labeled data. In this work, we compare SAM methods for the task of automatic tre"},"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":"2503.20199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T03:45:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"214fb56cf3bd9cad7eb6491ce2d312402b82cd17da2be1012ad42169547a07db","abstract_canon_sha256":"2b6c5f47996244ec85f4d2241606119ee7b16859f1fb419981e499b079109cc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:34.535130Z","signature_b64":"YhhM5KQfeaPbEUhGk6bRuNc30JVNOKkE/qS4Ttax8KTZDJxKdlLfZUhvD5t8BhD79c0o5Z5IoenNLj+2AlPSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9af7ea3f21ca7f8bda43dff72c8b66a1b51405e1a299665e848ba2bd7eaa10cc","last_reissued_at":"2026-07-05T10:39:34.534636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:34.534636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arthur Ouaknine, David Rolnick, Etienne Lalibert\\'e, Hugo Larochelle, M\\'elisande Teng, Yoshua Bengio","submitted_at":"2025-03-26T03:45:36Z","abstract_excerpt":"The potential of tree planting as a natural climate solution is often undermined by inadequate monitoring of tree planting projects. Current monitoring methods involve measuring trees by hand for each species, requiring extensive cost, time, and labour. Advances in drone remote sensing and computer vision offer great potential for mapping and characterizing trees from aerial imagery, and large pre-trained vision models, such as the Segment Anything Model (SAM), may be a particularly compelling choice given limited labeled data. In this work, we compare SAM methods for the task of automatic tre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20199","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.20199/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":"2503.20199","created_at":"2026-07-05T10:39:34.534699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20199v1","created_at":"2026-07-05T10:39:34.534699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20199","created_at":"2026-07-05T10:39:34.534699+00:00"},{"alias_kind":"pith_short_12","alias_value":"TL36UPZBZJ7Y","created_at":"2026-07-05T10:39:34.534699+00:00"},{"alias_kind":"pith_short_16","alias_value":"TL36UPZBZJ7YXWSD","created_at":"2026-07-05T10:39:34.534699+00:00"},{"alias_kind":"pith_short_8","alias_value":"TL36UPZB","created_at":"2026-07-05T10:39:34.534699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.00470","citing_title":"FG-TreeSeg: Flow-Guided Tree Crown Segmentation without Instance Annotations","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00170","citing_title":"SelvaBox: A high-resolution dataset for tropical tree crown detection","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG","json":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG.json","graph_json":"https://pith.science/api/pith-number/TL36UPZBZJ7YXWSD373SZC3GUG/graph.json","events_json":"https://pith.science/api/pith-number/TL36UPZBZJ7YXWSD373SZC3GUG/events.json","paper":"https://pith.science/paper/TL36UPZB"},"agent_actions":{"view_html":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG","download_json":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG.json","view_paper":"https://pith.science/paper/TL36UPZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20199&json=true","fetch_graph":"https://pith.science/api/pith-number/TL36UPZBZJ7YXWSD373SZC3GUG/graph.json","fetch_events":"https://pith.science/api/pith-number/TL36UPZBZJ7YXWSD373SZC3GUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG/action/storage_attestation","attest_author":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG/action/author_attestation","sign_citation":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG/action/citation_signature","submit_replication":"https://pith.science/pith/TL36UPZBZJ7YXWSD373SZC3GUG/action/replication_record"}},"created_at":"2026-07-05T10:39:34.534699+00:00","updated_at":"2026-07-05T10:39:34.534699+00:00"}