{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SFHG6S2WZUQKGLGQ5S226QOMIR","short_pith_number":"pith:SFHG6S2W","schema_version":"1.0","canonical_sha256":"914e6f4b56cd20a32cd0ecb5af41cc4440d90d8b36d1f5382349865e2d0c5d7e","source":{"kind":"arxiv","id":"2606.06485","version":1},"attestation_state":"computed","paper":{"title":"PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liujuan Cao, Shaohui Dai, Shengchuan Zhang, Yansong Qu, You Shen","submitted_at":"2026-06-04T17:59:04Z","abstract_excerpt":"Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, reason about, and ground both objects and their parts in 3D scenes. To enable training and evaluation"},"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":"2606.06485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T17:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"35c36f40ee1720488ca4b515e5e8a2492366216b9476869332ec7a1069d06833","abstract_canon_sha256":"1686b167685fd81399fde5dc6d904c36113eb83931a11015d159b56d7af64832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:46.929030Z","signature_b64":"+0fAdp2fiRU8GO0LjQH2bo7mQ7vZnnulscQ/gkkFCJQg5s7uzC5kofRv4lhiAnFRma8P71YqqUpGnPGDTVk/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"914e6f4b56cd20a32cd0ecb5af41cc4440d90d8b36d1f5382349865e2d0c5d7e","last_reissued_at":"2026-06-05T01:15:46.928629Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:46.928629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liujuan Cao, Shaohui Dai, Shengchuan Zhang, Yansong Qu, You Shen","submitted_at":"2026-06-04T17:59:04Z","abstract_excerpt":"Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, reason about, and ground both objects and their parts in 3D scenes. To enable training and evaluation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06485","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/2606.06485/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":"2606.06485","created_at":"2026-06-05T01:15:46.928693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06485v1","created_at":"2026-06-05T01:15:46.928693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06485","created_at":"2026-06-05T01:15:46.928693+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFHG6S2WZUQK","created_at":"2026-06-05T01:15:46.928693+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFHG6S2WZUQKGLGQ","created_at":"2026-06-05T01:15:46.928693+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFHG6S2W","created_at":"2026-06-05T01:15:46.928693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR","json":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR.json","graph_json":"https://pith.science/api/pith-number/SFHG6S2WZUQKGLGQ5S226QOMIR/graph.json","events_json":"https://pith.science/api/pith-number/SFHG6S2WZUQKGLGQ5S226QOMIR/events.json","paper":"https://pith.science/paper/SFHG6S2W"},"agent_actions":{"view_html":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR","download_json":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR.json","view_paper":"https://pith.science/paper/SFHG6S2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06485&json=true","fetch_graph":"https://pith.science/api/pith-number/SFHG6S2WZUQKGLGQ5S226QOMIR/graph.json","fetch_events":"https://pith.science/api/pith-number/SFHG6S2WZUQKGLGQ5S226QOMIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR/action/storage_attestation","attest_author":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR/action/author_attestation","sign_citation":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR/action/citation_signature","submit_replication":"https://pith.science/pith/SFHG6S2WZUQKGLGQ5S226QOMIR/action/replication_record"}},"created_at":"2026-06-05T01:15:46.928693+00:00","updated_at":"2026-06-05T01:15:46.928693+00:00"}