{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XBT7QP7RBDFDXG6QIWWOXEHQVT","short_pith_number":"pith:XBT7QP7R","schema_version":"1.0","canonical_sha256":"b867f83ff108ca3b9bd045aceb90f0acc8f1d77329bb3ff9d44d4678f588c345","source":{"kind":"arxiv","id":"2507.05515","version":2},"attestation_state":"computed","paper":{"title":"LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Chuang Yu, Haochen Huang, Jiahuan Pei, Junxiao Wang, Mohammad Aliannejadi, Moonisa Ahsan, Pablo Cesar, Xin Sun, Zhaochun Ren","submitted_at":"2025-07-07T22:29:01Z","abstract_excerpt":"Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we explore LEGO Co-builder, a hybrid benchmark combining real-world LEGO assembly logic with programmatically generated multimodal scenes. The dataset captures stepwise visual states and procedural instructions, allowing controlled evaluation of instruction-following, object detection, and state detection. We introduce a unified framework and assess leading VLMs su"},"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":"2507.05515","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T22:29:01Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"61f999f172635b64958106a402f6ce8d5e5201b9219b4c4fe89dbb5d56949f88","abstract_canon_sha256":"621673460073877dd9eea92d1fb7301dbe21122b3d7270bf5f3d8e2734825c7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:44.029557Z","signature_b64":"aGfNe/zR1z7+6H4NTC6s+Zdq+wcpt1hwJc12b6MV4NQdxEI5rEcgK427Tx+VtkjhKTc7gWT8Ue3EEg+QRv4YCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b867f83ff108ca3b9bd045aceb90f0acc8f1d77329bb3ff9d44d4678f588c345","last_reissued_at":"2026-07-05T11:41:44.029056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:44.029056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Chuang Yu, Haochen Huang, Jiahuan Pei, Junxiao Wang, Mohammad Aliannejadi, Moonisa Ahsan, Pablo Cesar, Xin Sun, Zhaochun Ren","submitted_at":"2025-07-07T22:29:01Z","abstract_excerpt":"Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we explore LEGO Co-builder, a hybrid benchmark combining real-world LEGO assembly logic with programmatically generated multimodal scenes. The dataset captures stepwise visual states and procedural instructions, allowing controlled evaluation of instruction-following, object detection, and state detection. We introduce a unified framework and assess leading VLMs su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05515","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/2507.05515/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":"2507.05515","created_at":"2026-07-05T11:41:44.029116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05515v2","created_at":"2026-07-05T11:41:44.029116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05515","created_at":"2026-07-05T11:41:44.029116+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBT7QP7RBDFD","created_at":"2026-07-05T11:41:44.029116+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBT7QP7RBDFDXG6Q","created_at":"2026-07-05T11:41:44.029116+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBT7QP7R","created_at":"2026-07-05T11:41:44.029116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05445","citing_title":"Brick-Composer: Using MLLMs for Assembly with Diverse Bricks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12845","citing_title":"AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07649","citing_title":"Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07649","citing_title":"Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT","json":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT.json","graph_json":"https://pith.science/api/pith-number/XBT7QP7RBDFDXG6QIWWOXEHQVT/graph.json","events_json":"https://pith.science/api/pith-number/XBT7QP7RBDFDXG6QIWWOXEHQVT/events.json","paper":"https://pith.science/paper/XBT7QP7R"},"agent_actions":{"view_html":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT","download_json":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT.json","view_paper":"https://pith.science/paper/XBT7QP7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05515&json=true","fetch_graph":"https://pith.science/api/pith-number/XBT7QP7RBDFDXG6QIWWOXEHQVT/graph.json","fetch_events":"https://pith.science/api/pith-number/XBT7QP7RBDFDXG6QIWWOXEHQVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT/action/storage_attestation","attest_author":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT/action/author_attestation","sign_citation":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT/action/citation_signature","submit_replication":"https://pith.science/pith/XBT7QP7RBDFDXG6QIWWOXEHQVT/action/replication_record"}},"created_at":"2026-07-05T11:41:44.029116+00:00","updated_at":"2026-07-05T11:41:44.029116+00:00"}