{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KK4GOEC6QUYUL6O4MDPO3XNA5T","short_pith_number":"pith:KK4GOEC6","schema_version":"1.0","canonical_sha256":"52b867105e853145f9dc60deeddda0ecf14846e3c30eb211ef9edf0f24397af1","source":{"kind":"arxiv","id":"2606.19828","version":1},"attestation_state":"computed","paper":{"title":"3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C.-C. Jay Kuo, Jingwen Chen, Jintang Xue, Xinyu Wang, Yixing Wu","submitted_at":"2026-06-18T06:12:59Z","abstract_excerpt":"3D multimodal large language models (3D MLLMs) describe a 3D object as a whole but cannot address, name, or reason about its parts. Prior part-aware attempts add segmentation decoders, heavier 3D encoders, or bounding-box grammars at substantial parameter cost. We take a fundamentally different path: we reorganize the input token stream so that parts become directly addressable through the LLM's own vocabulary. Our model, 3D-PLOT-LLM, partitions the frozen point encoder's patches into K locally coherent regions and inserts, before each region's patch tokens, a learnable per-region marker and a"},"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":"2606.19828","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T06:12:59Z","cross_cats_sorted":[],"title_canon_sha256":"ec54d1c6ea8e097cc59e5f53f2abc7273e8420ea9fc9af1eca34085eb2506137","abstract_canon_sha256":"1c21631251779972a08655318fe3b52e141899a8769b4742ad1c6cb4f9c6dec3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:36.376956Z","signature_b64":"IW3tBXxU5QiEwL/ca7gAlrIL3p937mEr5Et5V6BD4CM3goDIV86qyPaIZvxPAsfV+o4oSYCx+oU7Xk3X3v1NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b867105e853145f9dc60deeddda0ecf14846e3c30eb211ef9edf0f24397af1","last_reissued_at":"2026-06-19T16:12:36.376612Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:36.376612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C.-C. Jay Kuo, Jingwen Chen, Jintang Xue, Xinyu Wang, Yixing Wu","submitted_at":"2026-06-18T06:12:59Z","abstract_excerpt":"3D multimodal large language models (3D MLLMs) describe a 3D object as a whole but cannot address, name, or reason about its parts. Prior part-aware attempts add segmentation decoders, heavier 3D encoders, or bounding-box grammars at substantial parameter cost. We take a fundamentally different path: we reorganize the input token stream so that parts become directly addressable through the LLM's own vocabulary. Our model, 3D-PLOT-LLM, partitions the frozen point encoder's patches into K locally coherent regions and inserts, before each region's patch tokens, a learnable per-region marker and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19828","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/2606.19828/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":"2606.19828","created_at":"2026-06-19T16:12:36.376674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19828v1","created_at":"2026-06-19T16:12:36.376674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19828","created_at":"2026-06-19T16:12:36.376674+00:00"},{"alias_kind":"pith_short_12","alias_value":"KK4GOEC6QUYU","created_at":"2026-06-19T16:12:36.376674+00:00"},{"alias_kind":"pith_short_16","alias_value":"KK4GOEC6QUYUL6O4","created_at":"2026-06-19T16:12:36.376674+00:00"},{"alias_kind":"pith_short_8","alias_value":"KK4GOEC6","created_at":"2026-06-19T16:12:36.376674+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/KK4GOEC6QUYUL6O4MDPO3XNA5T","json":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T.json","graph_json":"https://pith.science/api/pith-number/KK4GOEC6QUYUL6O4MDPO3XNA5T/graph.json","events_json":"https://pith.science/api/pith-number/KK4GOEC6QUYUL6O4MDPO3XNA5T/events.json","paper":"https://pith.science/paper/KK4GOEC6"},"agent_actions":{"view_html":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T","download_json":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T.json","view_paper":"https://pith.science/paper/KK4GOEC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19828&json=true","fetch_graph":"https://pith.science/api/pith-number/KK4GOEC6QUYUL6O4MDPO3XNA5T/graph.json","fetch_events":"https://pith.science/api/pith-number/KK4GOEC6QUYUL6O4MDPO3XNA5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T/action/storage_attestation","attest_author":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T/action/author_attestation","sign_citation":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T/action/citation_signature","submit_replication":"https://pith.science/pith/KK4GOEC6QUYUL6O4MDPO3XNA5T/action/replication_record"}},"created_at":"2026-06-19T16:12:36.376674+00:00","updated_at":"2026-06-19T16:12:36.376674+00:00"}