{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JSMDA3SZOPPWD2FRUN3CN3YYFJ","short_pith_number":"pith:JSMDA3SZ","schema_version":"1.0","canonical_sha256":"4c98306e5973df61e8b1a37626ef182a6ced788a5fee99a6dab48f13d28a47fa","source":{"kind":"arxiv","id":"2607.18488","version":1},"attestation_state":"computed","paper":{"title":"The Open Ant: A Robot Platform for Reinforcement Learning Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Elena Sorina Lupu, John D. Martin, Joseph Modayil, Khurram Javed, Kris De Asis, Martha Steenstrup, Patrick Spieler","submitted_at":"2026-07-20T20:18:29Z","abstract_excerpt":"Reinforcement learning (RL) research has demonstrated success in both physical and simulated domains; however, the predominant methodology remains rooted in simulations. The predominance of simulations makes translating research to physical reality uncertain for both algorithms and researchers. We propose a physical platform that is designed to simplify the transition. In this paper, we present the Open Ant: a physical variant of the commonly used Gymnasium Ant environment, along with a simulation. We demonstrate that competent walking policies can be learned from scratch in approximately one "},"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":"2607.18488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-20T20:18:29Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"c89456e1556fe5ed213b025b2745dc41439cf4c447266f460fff3b31abba74aa","abstract_canon_sha256":"4b8a8917f3e9432f176cf16edf4b91f6059bff59a11977628f1411cd771e99bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:51.176585Z","signature_b64":"U8zVWUK7JhzZJ6+bLjOtOal6HGNb8drxI3T4MoBtEeN9BydHo9ITfU787M4HD5uHfj+G1Q5ff2bYZcEMOBdrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c98306e5973df61e8b1a37626ef182a6ced788a5fee99a6dab48f13d28a47fa","last_reissued_at":"2026-07-22T00:22:51.175765Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:51.175765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Open Ant: A Robot Platform for Reinforcement Learning Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Elena Sorina Lupu, John D. Martin, Joseph Modayil, Khurram Javed, Kris De Asis, Martha Steenstrup, Patrick Spieler","submitted_at":"2026-07-20T20:18:29Z","abstract_excerpt":"Reinforcement learning (RL) research has demonstrated success in both physical and simulated domains; however, the predominant methodology remains rooted in simulations. The predominance of simulations makes translating research to physical reality uncertain for both algorithms and researchers. We propose a physical platform that is designed to simplify the transition. In this paper, we present the Open Ant: a physical variant of the commonly used Gymnasium Ant environment, along with a simulation. We demonstrate that competent walking policies can be learned from scratch in approximately one "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18488","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/2607.18488/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":"2607.18488","created_at":"2026-07-22T00:22:51.176191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18488v1","created_at":"2026-07-22T00:22:51.176191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18488","created_at":"2026-07-22T00:22:51.176191+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSMDA3SZOPPW","created_at":"2026-07-22T00:22:51.176191+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSMDA3SZOPPWD2FR","created_at":"2026-07-22T00:22:51.176191+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSMDA3SZ","created_at":"2026-07-22T00:22:51.176191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ","json":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ.json","graph_json":"https://pith.science/api/pith-number/JSMDA3SZOPPWD2FRUN3CN3YYFJ/graph.json","events_json":"https://pith.science/api/pith-number/JSMDA3SZOPPWD2FRUN3CN3YYFJ/events.json","paper":"https://pith.science/paper/JSMDA3SZ"},"agent_actions":{"view_html":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ","download_json":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ.json","view_paper":"https://pith.science/paper/JSMDA3SZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18488&json=true","fetch_graph":"https://pith.science/api/pith-number/JSMDA3SZOPPWD2FRUN3CN3YYFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JSMDA3SZOPPWD2FRUN3CN3YYFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ/action/storage_attestation","attest_author":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ/action/author_attestation","sign_citation":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ/action/citation_signature","submit_replication":"https://pith.science/pith/JSMDA3SZOPPWD2FRUN3CN3YYFJ/action/replication_record"}},"created_at":"2026-07-22T00:22:51.176191+00:00","updated_at":"2026-07-22T00:22:51.176191+00:00"}