{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FXH6KBILPX7FWBVXC2CRWW2C6I","short_pith_number":"pith:FXH6KBIL","schema_version":"1.0","canonical_sha256":"2dcfe5050b7dfe5b06b716851b5b42f22bcb65d1f9e31502f97724f018a35e7d","source":{"kind":"arxiv","id":"2406.08973","version":3},"attestation_state":"computed","paper":{"title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Nikulin, Alexey Zemtsov, Ilya Zisman, Vladislav Kurenkov","submitted_at":"2024-06-13T10:04:17Z","abstract_excerpt":"Following the success of the in-context learning paradigm in large-scale language and computer vision models, the recently emerging field of in-context reinforcement learning is experiencing a rapid growth. However, its development has been held back by the lack of challenging benchmarks, as all the experiments have been carried out in simple environments and on small-scale datasets. We present XLand-100B, a large-scale dataset for in-context reinforcement learning based on the XLand-MiniGrid environment, as a first step to alleviate this problem. It contains complete learning histories for ne"},"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":"2406.08973","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T10:04:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8a0599fbe97203d32b7f2e4f925aa8fff78b9254fbd05ead2b9de2ca7b498fe","abstract_canon_sha256":"7296729b6be6a415b78537fcdede97784aaf084ec6475b602e64b13838f7572b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:00.828251Z","signature_b64":"CIh7CxrovJioaMwE9Z1PNFEEjo6lVxJxmL0nrOmv2f7vI0+R1ZEkCpta9tUqpgdDsoBMdpeL0jv0JngrGEn/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dcfe5050b7dfe5b06b716851b5b42f22bcb65d1f9e31502f97724f018a35e7d","last_reissued_at":"2026-07-05T10:22:00.827487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:00.827487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Nikulin, Alexey Zemtsov, Ilya Zisman, Vladislav Kurenkov","submitted_at":"2024-06-13T10:04:17Z","abstract_excerpt":"Following the success of the in-context learning paradigm in large-scale language and computer vision models, the recently emerging field of in-context reinforcement learning is experiencing a rapid growth. However, its development has been held back by the lack of challenging benchmarks, as all the experiments have been carried out in simple environments and on small-scale datasets. We present XLand-100B, a large-scale dataset for in-context reinforcement learning based on the XLand-MiniGrid environment, as a first step to alleviate this problem. It contains complete learning histories for ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08973","kind":"arxiv","version":3},"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/2406.08973/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":"2406.08973","created_at":"2026-07-05T10:22:00.827579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08973v3","created_at":"2026-07-05T10:22:00.827579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08973","created_at":"2026-07-05T10:22:00.827579+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXH6KBILPX7F","created_at":"2026-07-05T10:22:00.827579+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXH6KBILPX7FWBVX","created_at":"2026-07-05T10:22:00.827579+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXH6KBIL","created_at":"2026-07-05T10:22:00.827579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.06009","citing_title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I","json":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I.json","graph_json":"https://pith.science/api/pith-number/FXH6KBILPX7FWBVXC2CRWW2C6I/graph.json","events_json":"https://pith.science/api/pith-number/FXH6KBILPX7FWBVXC2CRWW2C6I/events.json","paper":"https://pith.science/paper/FXH6KBIL"},"agent_actions":{"view_html":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I","download_json":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I.json","view_paper":"https://pith.science/paper/FXH6KBIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08973&json=true","fetch_graph":"https://pith.science/api/pith-number/FXH6KBILPX7FWBVXC2CRWW2C6I/graph.json","fetch_events":"https://pith.science/api/pith-number/FXH6KBILPX7FWBVXC2CRWW2C6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I/action/storage_attestation","attest_author":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I/action/author_attestation","sign_citation":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I/action/citation_signature","submit_replication":"https://pith.science/pith/FXH6KBILPX7FWBVXC2CRWW2C6I/action/replication_record"}},"created_at":"2026-07-05T10:22:00.827579+00:00","updated_at":"2026-07-05T10:22:00.827579+00:00"}