{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RUKTDIPDDBPOG2UY4OIWTTIXPE","short_pith_number":"pith:RUKTDIPD","schema_version":"1.0","canonical_sha256":"8d1531a1e3185ee36a98e39169cd17790d72a17233171958f9cc22a8263d1af8","source":{"kind":"arxiv","id":"2604.08983","version":2},"attestation_state":"computed","paper":{"title":"AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"AssemLM integrates point clouds into a multimodal LLM via a specialized encoder to predict accurate 6D poses for robotic assembly.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenjia Bai, Huazhe Xu, Jicong Ao, Jinbin Qiao, Ouyang Lu, Shuang Qiu, Yu-Gang Jiang, Zhi Jing","submitted_at":"2026-04-10T05:43:39Z","abstract_excerpt":"Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. Recent methods based on vision-language models (VLMs) largely rely on coarse 2D perception and struggle to perform accurate reasoning over complex 3D geometry. To address this limitation, we propose AssemLM, a spatial multimodal large language model for robotic assembly that integrates assembly manuals, point clouds, and textual instructions to predict task-critical 6D assembly poses with explicit geometric understanding. To bridge raw 3D perception "},"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":true},"canonical_record":{"source":{"id":"2604.08983","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-04-10T05:43:39Z","cross_cats_sorted":[],"title_canon_sha256":"b599b82fa37233a947dcbf24c5e451cc73f28d4baeed9f97dd1ab7732ec560a9","abstract_canon_sha256":"e5ec8dc8c49019ed9d3e229209b2ef73acdeac22594396bb3f14adeee27dfe55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:27.622786Z","signature_b64":"tdpN1HqGltxq4c0euLvYGA8EwLwGpycpybu6cb0kUhKVfMgmLshb8m5eKl+CZa9w/d41PnkgOHQCZSSZJ9ZNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d1531a1e3185ee36a98e39169cd17790d72a17233171958f9cc22a8263d1af8","last_reissued_at":"2026-06-12T01:09:27.622397Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:27.622397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"AssemLM integrates point clouds into a multimodal LLM via a specialized encoder to predict accurate 6D poses for robotic assembly.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenjia Bai, Huazhe Xu, Jicong Ao, Jinbin Qiao, Ouyang Lu, Shuang Qiu, Yu-Gang Jiang, Zhi Jing","submitted_at":"2026-04-10T05:43:39Z","abstract_excerpt":"Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. Recent methods based on vision-language models (VLMs) largely rely on coarse 2D perception and struggle to perform accurate reasoning over complex 3D geometry. To address this limitation, we propose AssemLM, a spatial multimodal large language model for robotic assembly that integrates assembly manuals, point clouds, and textual instructions to predict task-critical 6D assembly poses with explicit geometric understanding. To bridge raw 3D perception "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AssemLM achieves state-of-the-art performance in 6D pose reasoning across diverse assembly scenarios. Furthermore, real-robot evaluations show that our model can support fine-grained and multi-step assembly execution in real-world settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the specialized point cloud encoder successfully captures fine-grained geometric and rotational features which integrate effectively with the multimodal language model to produce accurate 3D spatial reasoning that generalizes to real robots.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AssemLM uses a specialized point cloud encoder inside a multimodal LLM to reach state-of-the-art 6D pose prediction for assembly tasks, backed by a new 900K-sample benchmark called AssemBench.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AssemLM integrates point clouds into a multimodal LLM via a specialized encoder to predict accurate 6D poses for robotic assembly.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e97f4fb389520af028c1340d6d51effda8ad86072260a396ac92c21591946e05"},"source":{"id":"2604.08983","kind":"arxiv","version":2},"verdict":{"id":"11a06097-b50f-4c8c-8939-54249a68bbdb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:19:37.665077Z","strongest_claim":"AssemLM achieves state-of-the-art performance in 6D pose reasoning across diverse assembly scenarios. Furthermore, real-robot evaluations show that our model can support fine-grained and multi-step assembly execution in real-world settings.","one_line_summary":"AssemLM uses a specialized point cloud encoder inside a multimodal LLM to reach state-of-the-art 6D pose prediction for assembly tasks, backed by a new 900K-sample benchmark called AssemBench.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the specialized point cloud encoder successfully captures fine-grained geometric and rotational features which integrate effectively with the multimodal language model to produce accurate 3D spatial reasoning that generalizes to real robots.","pith_extraction_headline":"AssemLM integrates point clouds into a multimodal LLM via a specialized encoder to predict accurate 6D poses for robotic assembly."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08983/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":2,"snapshot_sha256":"026899e177bb977d6df1403293a491ada9876e0988f47a3e32063cdd68caca2a"},"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":"2604.08983","created_at":"2026-06-12T01:09:27.622452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.08983v2","created_at":"2026-06-12T01:09:27.622452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08983","created_at":"2026-06-12T01:09:27.622452+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUKTDIPDDBPO","created_at":"2026-06-12T01:09:27.622452+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUKTDIPDDBPOG2UY","created_at":"2026-06-12T01:09:27.622452+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUKTDIPD","created_at":"2026-06-12T01:09:27.622452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE","json":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE.json","graph_json":"https://pith.science/api/pith-number/RUKTDIPDDBPOG2UY4OIWTTIXPE/graph.json","events_json":"https://pith.science/api/pith-number/RUKTDIPDDBPOG2UY4OIWTTIXPE/events.json","paper":"https://pith.science/paper/RUKTDIPD"},"agent_actions":{"view_html":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE","download_json":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE.json","view_paper":"https://pith.science/paper/RUKTDIPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.08983&json=true","fetch_graph":"https://pith.science/api/pith-number/RUKTDIPDDBPOG2UY4OIWTTIXPE/graph.json","fetch_events":"https://pith.science/api/pith-number/RUKTDIPDDBPOG2UY4OIWTTIXPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE/action/storage_attestation","attest_author":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE/action/author_attestation","sign_citation":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE/action/citation_signature","submit_replication":"https://pith.science/pith/RUKTDIPDDBPOG2UY4OIWTTIXPE/action/replication_record"}},"created_at":"2026-06-12T01:09:27.622452+00:00","updated_at":"2026-06-12T01:09:27.622452+00:00"}