{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GD2MXFC2G7X36ORSFNZUURRTY4","short_pith_number":"pith:GD2MXFC2","schema_version":"1.0","canonical_sha256":"30f4cb945a37efbf3a322b734a4633c71a9e9cd99dee04e349ec1d0557d54c42","source":{"kind":"arxiv","id":"2407.19396","version":1},"attestation_state":"computed","paper":{"title":"NAVIX: Scaling MiniGrid Environments with JAX","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Lu, Eduardo Pignatelli, Jarek Liesen, Laura Toni, Pablo Samuel Castro, Robert Tjarko Lange","submitted_at":"2024-07-28T04:39:18Z","abstract_excerpt":"As Deep Reinforcement Learning (Deep RL) research moves towards solving large-scale worlds, efficient environment simulations become crucial for rapid experimentation. However, most existing environments struggle to scale to high throughput, setting back meaningful progress. Interactions are typically computed on the CPU, limiting training speed and throughput, due to slower computation and communication overhead when distributing the task across multiple machines. Ultimately, Deep RL training is CPU-bound, and developing batched, fast, and scalable environments has become a frontier for progr"},"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":"2407.19396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-28T04:39:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3ac56e50759fc9323b0d1a6af79db97ed704848661d78ec6993b837afe45320","abstract_canon_sha256":"229bae50dadf19da3231856e01204de6d0eda9919929212a3c631567a8f6de18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:39.420800Z","signature_b64":"W20Dn20V7wyxBEPC3HAlJFpThHfAUKM1tNy9nWAgcAHNC6soEtNAUpKzaxnJ33jIHL/p5hyEMCJG/Cuk/fPzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30f4cb945a37efbf3a322b734a4633c71a9e9cd99dee04e349ec1d0557d54c42","last_reissued_at":"2026-07-05T08:49:39.420312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:39.420312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NAVIX: Scaling MiniGrid Environments with JAX","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Lu, Eduardo Pignatelli, Jarek Liesen, Laura Toni, Pablo Samuel Castro, Robert Tjarko Lange","submitted_at":"2024-07-28T04:39:18Z","abstract_excerpt":"As Deep Reinforcement Learning (Deep RL) research moves towards solving large-scale worlds, efficient environment simulations become crucial for rapid experimentation. However, most existing environments struggle to scale to high throughput, setting back meaningful progress. Interactions are typically computed on the CPU, limiting training speed and throughput, due to slower computation and communication overhead when distributing the task across multiple machines. Ultimately, Deep RL training is CPU-bound, and developing batched, fast, and scalable environments has become a frontier for progr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19396","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/2407.19396/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":"2407.19396","created_at":"2026-07-05T08:49:39.420379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19396v1","created_at":"2026-07-05T08:49:39.420379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19396","created_at":"2026-07-05T08:49:39.420379+00:00"},{"alias_kind":"pith_short_12","alias_value":"GD2MXFC2G7X3","created_at":"2026-07-05T08:49:39.420379+00:00"},{"alias_kind":"pith_short_16","alias_value":"GD2MXFC2G7X36ORS","created_at":"2026-07-05T08:49:39.420379+00:00"},{"alias_kind":"pith_short_8","alias_value":"GD2MXFC2","created_at":"2026-07-05T08:49:39.420379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20577","citing_title":"Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13554","citing_title":"Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4","json":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4.json","graph_json":"https://pith.science/api/pith-number/GD2MXFC2G7X36ORSFNZUURRTY4/graph.json","events_json":"https://pith.science/api/pith-number/GD2MXFC2G7X36ORSFNZUURRTY4/events.json","paper":"https://pith.science/paper/GD2MXFC2"},"agent_actions":{"view_html":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4","download_json":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4.json","view_paper":"https://pith.science/paper/GD2MXFC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19396&json=true","fetch_graph":"https://pith.science/api/pith-number/GD2MXFC2G7X36ORSFNZUURRTY4/graph.json","fetch_events":"https://pith.science/api/pith-number/GD2MXFC2G7X36ORSFNZUURRTY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4/action/storage_attestation","attest_author":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4/action/author_attestation","sign_citation":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4/action/citation_signature","submit_replication":"https://pith.science/pith/GD2MXFC2G7X36ORSFNZUURRTY4/action/replication_record"}},"created_at":"2026-07-05T08:49:39.420379+00:00","updated_at":"2026-07-05T08:49:39.420379+00:00"}