{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OFORABSKCV6VEKQ6HWLVKTRKDL","short_pith_number":"pith:OFORABSK","schema_version":"1.0","canonical_sha256":"715d10064a157d522a1e3d97554e2a1ac648dda5fcf14e0f29f9e51e598ee325","source":{"kind":"arxiv","id":"2402.14606","version":1},"attestation_state":"computed","paper":{"title":"Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Atalay Donat, Denis Blessing, Gerhard Neumann, Moritz Reuss, Rudolf Lioutikov, Xiaogang Jia, Xinkai Jiang","submitted_at":"2024-02-22T14:54:28Z","abstract_excerpt":"Imitation learning with human data has demonstrated remarkable success in teaching robots in a wide range of skills. However, the inherent diversity in human behavior leads to the emergence of multi-modal data distributions, thereby presenting a formidable challenge for existing imitation learning algorithms. Quantifying a model's capacity to capture and replicate this diversity effectively is still an open problem. In this work, we introduce simulation benchmark environments and the corresponding Datasets with Diverse human Demonstrations for Imitation Learning (D3IL), designed explicitly to "},"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":"2402.14606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-22T14:54:28Z","cross_cats_sorted":[],"title_canon_sha256":"2686e9cb0a18af2bdff2277f4fbea40a48821db1b1510ab68cbfbf27245956e8","abstract_canon_sha256":"78f60f6bb714f73b6cc18047b7676d2a96d83fef0ff0f2c6e6300d6605c33b3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:12.705202Z","signature_b64":"zMInXFvpiyx+1ulxn1Y/ATI+4rWU0py/14NGRp/RrbMdsHd5LjuDEKgFa2gIvGTAwUz2UnplRSe1E4h2Lr5uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"715d10064a157d522a1e3d97554e2a1ac648dda5fcf14e0f29f9e51e598ee325","last_reissued_at":"2026-07-05T07:48:12.704732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:12.704732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Atalay Donat, Denis Blessing, Gerhard Neumann, Moritz Reuss, Rudolf Lioutikov, Xiaogang Jia, Xinkai Jiang","submitted_at":"2024-02-22T14:54:28Z","abstract_excerpt":"Imitation learning with human data has demonstrated remarkable success in teaching robots in a wide range of skills. However, the inherent diversity in human behavior leads to the emergence of multi-modal data distributions, thereby presenting a formidable challenge for existing imitation learning algorithms. Quantifying a model's capacity to capture and replicate this diversity effectively is still an open problem. In this work, we introduce simulation benchmark environments and the corresponding Datasets with Diverse human Demonstrations for Imitation Learning (D3IL), designed explicitly to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14606","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/2402.14606/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":"2402.14606","created_at":"2026-07-05T07:48:12.704790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14606v1","created_at":"2026-07-05T07:48:12.704790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14606","created_at":"2026-07-05T07:48:12.704790+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFORABSKCV6V","created_at":"2026-07-05T07:48:12.704790+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFORABSKCV6VEKQ6","created_at":"2026-07-05T07:48:12.704790+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFORABSK","created_at":"2026-07-05T07:48:12.704790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29201","citing_title":"Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01151","citing_title":"Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2409.00588","citing_title":"Diffusion Policy Policy Optimization","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL","json":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL.json","graph_json":"https://pith.science/api/pith-number/OFORABSKCV6VEKQ6HWLVKTRKDL/graph.json","events_json":"https://pith.science/api/pith-number/OFORABSKCV6VEKQ6HWLVKTRKDL/events.json","paper":"https://pith.science/paper/OFORABSK"},"agent_actions":{"view_html":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL","download_json":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL.json","view_paper":"https://pith.science/paper/OFORABSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14606&json=true","fetch_graph":"https://pith.science/api/pith-number/OFORABSKCV6VEKQ6HWLVKTRKDL/graph.json","fetch_events":"https://pith.science/api/pith-number/OFORABSKCV6VEKQ6HWLVKTRKDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL/action/storage_attestation","attest_author":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL/action/author_attestation","sign_citation":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL/action/citation_signature","submit_replication":"https://pith.science/pith/OFORABSKCV6VEKQ6HWLVKTRKDL/action/replication_record"}},"created_at":"2026-07-05T07:48:12.704790+00:00","updated_at":"2026-07-05T07:48:12.704790+00:00"}