{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KGPVHTJU4TV3CHNBGFTH4RGSFY","short_pith_number":"pith:KGPVHTJU","schema_version":"1.0","canonical_sha256":"519f53cd34e4ebb11da131667e44d22e24aa49b69f68ccfb693ad940fede0f49","source":{"kind":"arxiv","id":"2111.02767","version":1},"attestation_state":"computed","paper":{"title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anita Gergely, Damien Vincent, Daniel Toyama, Hanna Yakubovich, Jeremiah Harmsen, L\\'eonard Hussenot, Nikola Momchev, Olivier Pietquin, Piotr Stanczyk, Raphael Marinier, Sabela Ramos, Sertan Girgin","submitted_at":"2021-11-04T11:48:19Z","abstract_excerpt":"We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (SDM) including Reinforcement Learning (RL), Learning from Demonstrations, Offline RL or Imitation Learning. RLDS enables not only reproducibility of existing research and easy generation of new datasets, but also accelerates novel research. By providing a standard and lossless format of datasets it enables to quickly test new algorithms on a wider range of tasks. The RLDS ecosystem makes it easy to share datasets wit"},"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":"2111.02767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T11:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"dbe9223206cae9fe19fd13c3a0261709e8f0da0bc9417cba69b01a699c79e6b4","abstract_canon_sha256":"5b35f1dbfde89109c827b67afdf751a72a3351fef91a15c6bdcecf737bbaffb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:08.573635Z","signature_b64":"LAjTJtsu3PUYDVnIgB0LfxMeZlS2qb5n+zXaDr3XT4+3u0dD2ZfSznwGDa0ot7PQUMqdjbhHtHvnWziET4v/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"519f53cd34e4ebb11da131667e44d22e24aa49b69f68ccfb693ad940fede0f49","last_reissued_at":"2026-07-05T03:29:08.573026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:08.573026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anita Gergely, Damien Vincent, Daniel Toyama, Hanna Yakubovich, Jeremiah Harmsen, L\\'eonard Hussenot, Nikola Momchev, Olivier Pietquin, Piotr Stanczyk, Raphael Marinier, Sabela Ramos, Sertan Girgin","submitted_at":"2021-11-04T11:48:19Z","abstract_excerpt":"We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (SDM) including Reinforcement Learning (RL), Learning from Demonstrations, Offline RL or Imitation Learning. RLDS enables not only reproducibility of existing research and easy generation of new datasets, but also accelerates novel research. By providing a standard and lossless format of datasets it enables to quickly test new algorithms on a wider range of tasks. The RLDS ecosystem makes it easy to share datasets wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02767","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/2111.02767/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":"2111.02767","created_at":"2026-07-05T03:29:08.573097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.02767v1","created_at":"2026-07-05T03:29:08.573097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02767","created_at":"2026-07-05T03:29:08.573097+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGPVHTJU4TV3","created_at":"2026-07-05T03:29:08.573097+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGPVHTJU4TV3CHNB","created_at":"2026-07-05T03:29:08.573097+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGPVHTJU","created_at":"2026-07-05T03:29:08.573097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01120","citing_title":"Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01120","citing_title":"Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30456","citing_title":"Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11236","citing_title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11564","citing_title":"RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11665","citing_title":"Nautilus: From One Prompt to Plug-and-Play Robot Learning","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26637","citing_title":"ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY","json":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY.json","graph_json":"https://pith.science/api/pith-number/KGPVHTJU4TV3CHNBGFTH4RGSFY/graph.json","events_json":"https://pith.science/api/pith-number/KGPVHTJU4TV3CHNBGFTH4RGSFY/events.json","paper":"https://pith.science/paper/KGPVHTJU"},"agent_actions":{"view_html":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY","download_json":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY.json","view_paper":"https://pith.science/paper/KGPVHTJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.02767&json=true","fetch_graph":"https://pith.science/api/pith-number/KGPVHTJU4TV3CHNBGFTH4RGSFY/graph.json","fetch_events":"https://pith.science/api/pith-number/KGPVHTJU4TV3CHNBGFTH4RGSFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY/action/storage_attestation","attest_author":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY/action/author_attestation","sign_citation":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY/action/citation_signature","submit_replication":"https://pith.science/pith/KGPVHTJU4TV3CHNBGFTH4RGSFY/action/replication_record"}},"created_at":"2026-07-05T03:29:08.573097+00:00","updated_at":"2026-07-05T03:29:08.573097+00:00"}