{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W43HXEXYDIW2BXYIFJDYKDLVZL","short_pith_number":"pith:W43HXEXY","schema_version":"1.0","canonical_sha256":"b7367b92f81a2da0df082a47850d75cacb3871c81cb56cf770ef0498aca7e4fe","source":{"kind":"arxiv","id":"2405.17427","version":2},"attestation_state":"computed","paper":{"title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuan-Chih Huang, Lu Qi, Ming-Hsuan Yang, Shuicheng Yan, Xiangtai Li","submitted_at":"2024-05-27T17:59:41Z","abstract_excerpt":"Recent advancements in multimodal large language models (LLMs) have demonstrated significant potential across various domains, particularly in concept reasoning. However, their applications in understanding 3D environments remain limited, primarily offering textual or numerical outputs without generating dense, informative segmentation masks. This paper introduces Reason3D, a novel LLM designed for comprehensive 3D understanding. Reason3D processes point cloud data and text prompts to produce textual responses and segmentation masks, enabling advanced tasks such as 3D reasoning segmentation, h"},"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":"2405.17427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"cd87f8cd63e7059d85221bea53185419d767f405650bc074fe0bdb7de9e3b006","abstract_canon_sha256":"c3281261a24679146ecc090b4d62cba66ee99b9f11d9116ff1e20ea7ad9d12aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:20.077853Z","signature_b64":"2AhqHGYzxsYzYyRZi8RoQjdA1CzYsPBH/A0/7n+rQctGcQaet1pBytdxOUGMtkqu0Q2zM/PWyR8l7BFw6pCkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7367b92f81a2da0df082a47850d75cacb3871c81cb56cf770ef0498aca7e4fe","last_reissued_at":"2026-07-05T10:11:20.077347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:20.077347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuan-Chih Huang, Lu Qi, Ming-Hsuan Yang, Shuicheng Yan, Xiangtai Li","submitted_at":"2024-05-27T17:59:41Z","abstract_excerpt":"Recent advancements in multimodal large language models (LLMs) have demonstrated significant potential across various domains, particularly in concept reasoning. However, their applications in understanding 3D environments remain limited, primarily offering textual or numerical outputs without generating dense, informative segmentation masks. This paper introduces Reason3D, a novel LLM designed for comprehensive 3D understanding. Reason3D processes point cloud data and text prompts to produce textual responses and segmentation masks, enabling advanced tasks such as 3D reasoning segmentation, h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17427","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/2405.17427/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":"2405.17427","created_at":"2026-07-05T10:11:20.077407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17427v2","created_at":"2026-07-05T10:11:20.077407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17427","created_at":"2026-07-05T10:11:20.077407+00:00"},{"alias_kind":"pith_short_12","alias_value":"W43HXEXYDIW2","created_at":"2026-07-05T10:11:20.077407+00:00"},{"alias_kind":"pith_short_16","alias_value":"W43HXEXYDIW2BXYI","created_at":"2026-07-05T10:11:20.077407+00:00"},{"alias_kind":"pith_short_8","alias_value":"W43HXEXY","created_at":"2026-07-05T10:11:20.077407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07781","citing_title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL","json":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL.json","graph_json":"https://pith.science/api/pith-number/W43HXEXYDIW2BXYIFJDYKDLVZL/graph.json","events_json":"https://pith.science/api/pith-number/W43HXEXYDIW2BXYIFJDYKDLVZL/events.json","paper":"https://pith.science/paper/W43HXEXY"},"agent_actions":{"view_html":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL","download_json":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL.json","view_paper":"https://pith.science/paper/W43HXEXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17427&json=true","fetch_graph":"https://pith.science/api/pith-number/W43HXEXYDIW2BXYIFJDYKDLVZL/graph.json","fetch_events":"https://pith.science/api/pith-number/W43HXEXYDIW2BXYIFJDYKDLVZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL/action/storage_attestation","attest_author":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL/action/author_attestation","sign_citation":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL/action/citation_signature","submit_replication":"https://pith.science/pith/W43HXEXYDIW2BXYIFJDYKDLVZL/action/replication_record"}},"created_at":"2026-07-05T10:11:20.077407+00:00","updated_at":"2026-07-05T10:11:20.077407+00:00"}