{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AFIZYN7Q4KPXV4SOQONWOJHWNO","short_pith_number":"pith:AFIZYN7Q","schema_version":"1.0","canonical_sha256":"01519c37f0e29f7af24e839b6724f66b9687c2f76bafb61cd19e0b7b0bd32408","source":{"kind":"arxiv","id":"2410.03645","version":1},"attestation_state":"computed","paper":{"title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Annabella Macaluso, Huazhe Xu, Lirui Wang, Minghuan Liu, Pu Hua, Weinan Zhang, Yunfeng Lin","submitted_at":"2024-10-04T17:51:33Z","abstract_excerpt":"Robotic simulation today remains challenging to scale up due to the human efforts required to create diverse simulation tasks and scenes. Simulation-trained policies also face scalability issues as many sim-to-real methods focus on a single task. To address these challenges, this work proposes GenSim2, a scalable framework that leverages coding LLMs with multi-modal and reasoning capabilities for complex and realistic simulation task creation, including long-horizon tasks with articulated objects. To automatically generate demonstration data for these tasks at scale, we propose planning and RL"},"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":"2410.03645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-04T17:51:33Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"8c1dbe2dd3a841d66e2d4cbb0fb52ca8643fc8111f7bc2ec0680339d2d2208c9","abstract_canon_sha256":"d2a5f573fd49c9231b52721626999f20ec770e89508b39a860d579ef471edbd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:04.177702Z","signature_b64":"+m87DmjdZsrhmFHJ8CkuVghyoP9v2u7pFCLyDVn4qR4krFA+f8erdEvLihTfPJY2D9m1WVmcIcZe9wJm3ZF+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01519c37f0e29f7af24e839b6724f66b9687c2f76bafb61cd19e0b7b0bd32408","last_reissued_at":"2026-07-05T09:16:04.177173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:04.177173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Annabella Macaluso, Huazhe Xu, Lirui Wang, Minghuan Liu, Pu Hua, Weinan Zhang, Yunfeng Lin","submitted_at":"2024-10-04T17:51:33Z","abstract_excerpt":"Robotic simulation today remains challenging to scale up due to the human efforts required to create diverse simulation tasks and scenes. Simulation-trained policies also face scalability issues as many sim-to-real methods focus on a single task. To address these challenges, this work proposes GenSim2, a scalable framework that leverages coding LLMs with multi-modal and reasoning capabilities for complex and realistic simulation task creation, including long-horizon tasks with articulated objects. To automatically generate demonstration data for these tasks at scale, we propose planning and RL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03645","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/2410.03645/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":"2410.03645","created_at":"2026-07-05T09:16:04.177232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03645v1","created_at":"2026-07-05T09:16:04.177232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03645","created_at":"2026-07-05T09:16:04.177232+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFIZYN7Q4KPX","created_at":"2026-07-05T09:16:04.177232+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFIZYN7Q4KPXV4SO","created_at":"2026-07-05T09:16:04.177232+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFIZYN7Q","created_at":"2026-07-05T09:16:04.177232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12207","citing_title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00054","citing_title":"From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08547","citing_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11674","citing_title":"AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11674","citing_title":"AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13800","citing_title":"EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO","json":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO.json","graph_json":"https://pith.science/api/pith-number/AFIZYN7Q4KPXV4SOQONWOJHWNO/graph.json","events_json":"https://pith.science/api/pith-number/AFIZYN7Q4KPXV4SOQONWOJHWNO/events.json","paper":"https://pith.science/paper/AFIZYN7Q"},"agent_actions":{"view_html":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO","download_json":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO.json","view_paper":"https://pith.science/paper/AFIZYN7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03645&json=true","fetch_graph":"https://pith.science/api/pith-number/AFIZYN7Q4KPXV4SOQONWOJHWNO/graph.json","fetch_events":"https://pith.science/api/pith-number/AFIZYN7Q4KPXV4SOQONWOJHWNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO/action/storage_attestation","attest_author":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO/action/author_attestation","sign_citation":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO/action/citation_signature","submit_replication":"https://pith.science/pith/AFIZYN7Q4KPXV4SOQONWOJHWNO/action/replication_record"}},"created_at":"2026-07-05T09:16:04.177232+00:00","updated_at":"2026-07-05T09:16:04.177232+00:00"}