{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJHAY6M35VFXY7Q75TRYTMMEFP","short_pith_number":"pith:XJHAY6M3","schema_version":"1.0","canonical_sha256":"ba4e0c799bed4b7c7e1fece389b1842bc41086365fd926451cd2b5fb3040eb38","source":{"kind":"arxiv","id":"2606.08206","version":1},"attestation_state":"computed","paper":{"title":"SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Maciej Wielgosz, Rasmus Astrup, Stefano Puliti","submitted_at":"2026-06-06T14:48:25Z","abstract_excerpt":"We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines a serialization-based Point Transformer v3 backbone with a lightweight semantic head and a tree-focused cross-attention mask decoder. Semantic predictions restrict instance decoding to tree-class voxels, while instance-aware query initialization, one-to-many seed supervision, and asymmetric mask scoring improve separation in dense and structurally complex stands. We further introduce FOR-instance v3, an expanded benchmark comprising 427 scenes"},"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":"2606.08206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T14:48:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"edd49d85f15962b712053869a00699bc30a70a5e55ed78125ce55f6c0df5dd04","abstract_canon_sha256":"597487cda9d0b57006943ad2756e5c0eb1f9887dec3a29a234d44d666bc663e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:30.049702Z","signature_b64":"RG9WA+Vm0oNmOvrkC5bh/SZEjsrdtDQ6j+CIys0BBZo1t/9YEUCnoOdbPEFWtDtIrRY0r96Z9fpMZRXQScjrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba4e0c799bed4b7c7e1fece389b1842bc41086365fd926451cd2b5fb3040eb38","last_reissued_at":"2026-06-09T01:05:30.049086Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:30.049086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Maciej Wielgosz, Rasmus Astrup, Stefano Puliti","submitted_at":"2026-06-06T14:48:25Z","abstract_excerpt":"We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines a serialization-based Point Transformer v3 backbone with a lightweight semantic head and a tree-focused cross-attention mask decoder. Semantic predictions restrict instance decoding to tree-class voxels, while instance-aware query initialization, one-to-many seed supervision, and asymmetric mask scoring improve separation in dense and structurally complex stands. We further introduce FOR-instance v3, an expanded benchmark comprising 427 scenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08206","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/2606.08206/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":"2606.08206","created_at":"2026-06-09T01:05:30.049177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08206v1","created_at":"2026-06-09T01:05:30.049177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08206","created_at":"2026-06-09T01:05:30.049177+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJHAY6M35VFX","created_at":"2026-06-09T01:05:30.049177+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJHAY6M35VFXY7Q7","created_at":"2026-06-09T01:05:30.049177+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJHAY6M3","created_at":"2026-06-09T01:05:30.049177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27491","citing_title":"SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP","json":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP.json","graph_json":"https://pith.science/api/pith-number/XJHAY6M35VFXY7Q75TRYTMMEFP/graph.json","events_json":"https://pith.science/api/pith-number/XJHAY6M35VFXY7Q75TRYTMMEFP/events.json","paper":"https://pith.science/paper/XJHAY6M3"},"agent_actions":{"view_html":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP","download_json":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP.json","view_paper":"https://pith.science/paper/XJHAY6M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08206&json=true","fetch_graph":"https://pith.science/api/pith-number/XJHAY6M35VFXY7Q75TRYTMMEFP/graph.json","fetch_events":"https://pith.science/api/pith-number/XJHAY6M35VFXY7Q75TRYTMMEFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP/action/storage_attestation","attest_author":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP/action/author_attestation","sign_citation":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP/action/citation_signature","submit_replication":"https://pith.science/pith/XJHAY6M35VFXY7Q75TRYTMMEFP/action/replication_record"}},"created_at":"2026-06-09T01:05:30.049177+00:00","updated_at":"2026-06-09T01:05:30.049177+00:00"}