{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQ7DQSCIXPWZGOYL27ZGYIDTIK","short_pith_number":"pith:ZQ7DQSCI","schema_version":"1.0","canonical_sha256":"cc3e384848bbed933b0bd7f26c2073428bc4293a04f346c94afa15a51e2450b4","source":{"kind":"arxiv","id":"2606.05445","version":1},"attestation_state":"computed","paper":{"title":"Brick-Composer: Using MLLMs for Assembly with Diverse Bricks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingxuan Li, Cheng Qian, Denghui Zhang, Heng Ji, Jiateng Liu, Jiayu Liu, Kaiwen Hong, Katherine Driggs-Campbell, Manling Li, Rushi Wang, Zhenhailong Wang","submitted_at":"2026-06-03T21:08:06Z","abstract_excerpt":"We dream of AI agents that can read arbitrary designs and construct real-world objects from reusable building blocks. As a first step toward this vision, we study whether multimodal large language models (MLLMs) possess the visual grounding and spatial reasoning capabilities required for brick assembly. We formulate brick assembly as a sequential decision-making problem, where each step involves two subtasks: brick selection, identifying the target brick from candidate components, and brick pose estimation, predicting where and how the selected brick should be placed. To support this study, we"},"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":"2606.05445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-03T21:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"8b87e8de893bf0749b08673e118952b0ac6aaa126a37099c1d9662b32714c846","abstract_canon_sha256":"2de918b869e62dbb865598bed7b34f03f52013897ae8b90c3aacc14b653d5556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:58.180447Z","signature_b64":"1geJR6x3zftwezh6k/KVW7cYObBqL3alcPhV83yMjN0YT16zZwMmkskoIWSDaVWVwo65HYslsDeh7qhcEY/pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3e384848bbed933b0bd7f26c2073428bc4293a04f346c94afa15a51e2450b4","last_reissued_at":"2026-06-05T00:13:58.179984Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:58.179984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Brick-Composer: Using MLLMs for Assembly with Diverse Bricks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingxuan Li, Cheng Qian, Denghui Zhang, Heng Ji, Jiateng Liu, Jiayu Liu, Kaiwen Hong, Katherine Driggs-Campbell, Manling Li, Rushi Wang, Zhenhailong Wang","submitted_at":"2026-06-03T21:08:06Z","abstract_excerpt":"We dream of AI agents that can read arbitrary designs and construct real-world objects from reusable building blocks. As a first step toward this vision, we study whether multimodal large language models (MLLMs) possess the visual grounding and spatial reasoning capabilities required for brick assembly. We formulate brick assembly as a sequential decision-making problem, where each step involves two subtasks: brick selection, identifying the target brick from candidate components, and brick pose estimation, predicting where and how the selected brick should be placed. To support this study, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05445","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/2606.05445/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":"2606.05445","created_at":"2026-06-05T00:13:58.180048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05445v1","created_at":"2026-06-05T00:13:58.180048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05445","created_at":"2026-06-05T00:13:58.180048+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ7DQSCIXPWZ","created_at":"2026-06-05T00:13:58.180048+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ7DQSCIXPWZGOYL","created_at":"2026-06-05T00:13:58.180048+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ7DQSCI","created_at":"2026-06-05T00:13:58.180048+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/ZQ7DQSCIXPWZGOYL27ZGYIDTIK","json":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK.json","graph_json":"https://pith.science/api/pith-number/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/graph.json","events_json":"https://pith.science/api/pith-number/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/events.json","paper":"https://pith.science/paper/ZQ7DQSCI"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK","download_json":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK.json","view_paper":"https://pith.science/paper/ZQ7DQSCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05445&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ7DQSCIXPWZGOYL27ZGYIDTIK/action/replication_record"}},"created_at":"2026-06-05T00:13:58.180048+00:00","updated_at":"2026-06-05T00:13:58.180048+00:00"}