{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M556G3KMVADNICYYRGUQS46R2P","short_pith_number":"pith:M556G3KM","schema_version":"1.0","canonical_sha256":"677be36d4ca806d40b1889a90973d1d3f4f645d309479000d188d1b570b6ed6d","source":{"kind":"arxiv","id":"2506.04837","version":1},"attestation_state":"computed","paper":{"title":"OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunshen Zhang","submitted_at":"2025-06-05T09:57:43Z","abstract_excerpt":"Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify target objects before executing visual recognition tasks. Such systems have matured significantly, demonstrating the ability to reason and comprehend implicit user intentions in two-dimensional contexts, producing accurate segmentation masks based on complex and implicit query text. However, a comparable framework and structure for 3D reasoning segmentation remain absent. This paper"},"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":"2506.04837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T09:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"5b3acb94e9281528732f03a185278f31328e9b1b2095dcae24cc24b8f24bf168","abstract_canon_sha256":"f7450ae5a43ac73bc198df5e6c50497cf6964c0b76e4f0f32920f5912a2cbf6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:37.510614Z","signature_b64":"7bjgi+kYwvuC5DvGM7CkMymHVDiZXIRUEkyDlIlhG6/69A66b9iTYkzUe3SQHvj6WF0EKvvBhZ+eyXW0XelRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"677be36d4ca806d40b1889a90973d1d3f4f645d309479000d188d1b570b6ed6d","last_reissued_at":"2026-07-05T11:16:37.510172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:37.510172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunshen Zhang","submitted_at":"2025-06-05T09:57:43Z","abstract_excerpt":"Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify target objects before executing visual recognition tasks. Such systems have matured significantly, demonstrating the ability to reason and comprehend implicit user intentions in two-dimensional contexts, producing accurate segmentation masks based on complex and implicit query text. However, a comparable framework and structure for 3D reasoning segmentation remain absent. This paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04837","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/2506.04837/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":"2506.04837","created_at":"2026-07-05T11:16:37.510236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04837v1","created_at":"2026-07-05T11:16:37.510236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04837","created_at":"2026-07-05T11:16:37.510236+00:00"},{"alias_kind":"pith_short_12","alias_value":"M556G3KMVADN","created_at":"2026-07-05T11:16:37.510236+00:00"},{"alias_kind":"pith_short_16","alias_value":"M556G3KMVADNICYY","created_at":"2026-07-05T11:16:37.510236+00:00"},{"alias_kind":"pith_short_8","alias_value":"M556G3KM","created_at":"2026-07-05T11:16:37.510236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P","json":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P.json","graph_json":"https://pith.science/api/pith-number/M556G3KMVADNICYYRGUQS46R2P/graph.json","events_json":"https://pith.science/api/pith-number/M556G3KMVADNICYYRGUQS46R2P/events.json","paper":"https://pith.science/paper/M556G3KM"},"agent_actions":{"view_html":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P","download_json":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P.json","view_paper":"https://pith.science/paper/M556G3KM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04837&json=true","fetch_graph":"https://pith.science/api/pith-number/M556G3KMVADNICYYRGUQS46R2P/graph.json","fetch_events":"https://pith.science/api/pith-number/M556G3KMVADNICYYRGUQS46R2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P/action/storage_attestation","attest_author":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P/action/author_attestation","sign_citation":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P/action/citation_signature","submit_replication":"https://pith.science/pith/M556G3KMVADNICYYRGUQS46R2P/action/replication_record"}},"created_at":"2026-07-05T11:16:37.510236+00:00","updated_at":"2026-07-05T11:16:37.510236+00:00"}