{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KAD5Z7J6TS4K3CXDGRPSJZ4KCG","short_pith_number":"pith:KAD5Z7J6","schema_version":"1.0","canonical_sha256":"5007dcfd3e9cb8ad8ae3345f24e78a11bd81414cb125f00083f14f01e36ba55b","source":{"kind":"arxiv","id":"2112.03227","version":4},"attestation_state":"computed","paper":{"title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Erick Rosete-Beas, Lukas Hermann, Oier Mees, Wolfram Burgard","submitted_at":"2021-12-06T18:37:33Z","abstract_excerpt":"General-purpose robots coexisting with humans in their environment must learn to relate human language to their perceptions and actions to be useful in a range of daily tasks. Moreover, they need to acquire a diverse repertoire of general-purpose skills that allow composing long-horizon tasks by following unconstrained language instructions. In this paper, we present CALVIN (Composing Actions from Language and Vision), an open-source simulated benchmark to learn long-horizon language-conditioned tasks. Our aim is to make it possible to develop agents that can solve many robotic manipulation ta"},"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":"2112.03227","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-06T18:37:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"9b18c8383bf78883188669be83a65fa8d1bb76a9c43ee3fe14a83adbde6d8bdb","abstract_canon_sha256":"d8248b056af409fb3c6d41316d7a1c568a18d3f838f82c1882c8c4a1d65bf702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:00.739439Z","signature_b64":"Zq3C0QKGfqO9QmWKIRrGtn6yUAdLbOivKXQNq4/gv4XEzT/rFVMctAoR7PvezLCYvdK7aP/FL56VmDNRcjMODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5007dcfd3e9cb8ad8ae3345f24e78a11bd81414cb125f00083f14f01e36ba55b","last_reissued_at":"2026-07-05T04:40:00.738880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:00.738880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Erick Rosete-Beas, Lukas Hermann, Oier Mees, Wolfram Burgard","submitted_at":"2021-12-06T18:37:33Z","abstract_excerpt":"General-purpose robots coexisting with humans in their environment must learn to relate human language to their perceptions and actions to be useful in a range of daily tasks. Moreover, they need to acquire a diverse repertoire of general-purpose skills that allow composing long-horizon tasks by following unconstrained language instructions. In this paper, we present CALVIN (Composing Actions from Language and Vision), an open-source simulated benchmark to learn long-horizon language-conditioned tasks. Our aim is to make it possible to develop agents that can solve many robotic manipulation ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03227","kind":"arxiv","version":4},"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/2112.03227/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":"2112.03227","created_at":"2026-07-05T04:40:00.738940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03227v4","created_at":"2026-07-05T04:40:00.738940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03227","created_at":"2026-07-05T04:40:00.738940+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAD5Z7J6TS4K","created_at":"2026-07-05T04:40:00.738940+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAD5Z7J6TS4K3CXD","created_at":"2026-07-05T04:40:00.738940+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAD5Z7J6","created_at":"2026-07-05T04:40:00.738940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19297","citing_title":"Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00089","citing_title":"Can Predicted Dynamics Exist in the Physical World?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18727","citing_title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20231","citing_title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25788","citing_title":"KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24622","citing_title":"CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06311","citing_title":"Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23001","citing_title":"Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11751","citing_title":"Grounded World Model for Semantically Generalizable Planning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16886","citing_title":"Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG","json":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG.json","graph_json":"https://pith.science/api/pith-number/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/graph.json","events_json":"https://pith.science/api/pith-number/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/events.json","paper":"https://pith.science/paper/KAD5Z7J6"},"agent_actions":{"view_html":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG","download_json":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG.json","view_paper":"https://pith.science/paper/KAD5Z7J6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03227&json=true","fetch_graph":"https://pith.science/api/pith-number/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/graph.json","fetch_events":"https://pith.science/api/pith-number/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/action/storage_attestation","attest_author":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/action/author_attestation","sign_citation":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/action/citation_signature","submit_replication":"https://pith.science/pith/KAD5Z7J6TS4K3CXDGRPSJZ4KCG/action/replication_record"}},"created_at":"2026-07-05T04:40:00.738940+00:00","updated_at":"2026-07-05T04:40:00.738940+00:00"}