{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HUQA63QUTPU2VRUOT3MOPZ3MNE","short_pith_number":"pith:HUQA63QU","schema_version":"1.0","canonical_sha256":"3d200f6e149be9aac68e9ed8e7e76c690e333ff0941ce2673d50b0401f1df49f","source":{"kind":"arxiv","id":"2507.00257","version":1},"attestation_state":"computed","paper":{"title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Maria Metelli, Alessio Russo, Davide Salaorni, Francesco Trov\\`o, Giovanni Dispoto, Giuseppe Calcagno, Marcello Restelli, Marco Mussi, Matteo Papini, Paolo Bonetti, Samuele Delpero, Vincenzo De Paola","submitted_at":"2025-06-30T20:47:50Z","abstract_excerpt":"In recent years, \\emph{Reinforcement Learning} (RL) has made remarkable progress, achieving superhuman performance in a wide range of simulated environments. As research moves toward deploying RL in real-world applications, the field faces a new set of challenges inherent to real-world settings, such as large state-action spaces, non-stationarity, and partial observability. Despite their importance, these challenges are often underexplored in current benchmarks, which tend to focus on idealized, fully observable, and stationary environments, often neglecting to incorporate real-world complexit"},"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":"2507.00257","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T20:47:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01014dbc209b15c63962a55eb8f29c7ccaadb0d94476af54adcc4e28ba76c94a","abstract_canon_sha256":"5d1668d18a9ba4e76ad4118c0af6310a0173ad5c1fc87913a8c1734c34a14511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:05.189703Z","signature_b64":"n9T74CJXfL9Q1kCaP9xWefkS2pzEeuxied5lUJB5g0gYdOdQQvt/+b11RYP/30vqFYvN+lJPORc2nVSZDoJ1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d200f6e149be9aac68e9ed8e7e76c690e333ff0941ce2673d50b0401f1df49f","last_reissued_at":"2026-07-05T11:30:05.189047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:05.189047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Maria Metelli, Alessio Russo, Davide Salaorni, Francesco Trov\\`o, Giovanni Dispoto, Giuseppe Calcagno, Marcello Restelli, Marco Mussi, Matteo Papini, Paolo Bonetti, Samuele Delpero, Vincenzo De Paola","submitted_at":"2025-06-30T20:47:50Z","abstract_excerpt":"In recent years, \\emph{Reinforcement Learning} (RL) has made remarkable progress, achieving superhuman performance in a wide range of simulated environments. As research moves toward deploying RL in real-world applications, the field faces a new set of challenges inherent to real-world settings, such as large state-action spaces, non-stationarity, and partial observability. Despite their importance, these challenges are often underexplored in current benchmarks, which tend to focus on idealized, fully observable, and stationary environments, often neglecting to incorporate real-world complexit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00257","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/2507.00257/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":"2507.00257","created_at":"2026-07-05T11:30:05.189124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00257v1","created_at":"2026-07-05T11:30:05.189124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00257","created_at":"2026-07-05T11:30:05.189124+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUQA63QUTPU2","created_at":"2026-07-05T11:30:05.189124+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUQA63QUTPU2VRUO","created_at":"2026-07-05T11:30:05.189124+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUQA63QU","created_at":"2026-07-05T11:30:05.189124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26627","citing_title":"Breaking the Epistemic Trap: Active Perception Under Compound Uncertainty","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26627","citing_title":"Breaking the Epistemic Trap: Active Perception Under Compound Uncertainty","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE","json":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE.json","graph_json":"https://pith.science/api/pith-number/HUQA63QUTPU2VRUOT3MOPZ3MNE/graph.json","events_json":"https://pith.science/api/pith-number/HUQA63QUTPU2VRUOT3MOPZ3MNE/events.json","paper":"https://pith.science/paper/HUQA63QU"},"agent_actions":{"view_html":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE","download_json":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE.json","view_paper":"https://pith.science/paper/HUQA63QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00257&json=true","fetch_graph":"https://pith.science/api/pith-number/HUQA63QUTPU2VRUOT3MOPZ3MNE/graph.json","fetch_events":"https://pith.science/api/pith-number/HUQA63QUTPU2VRUOT3MOPZ3MNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE/action/storage_attestation","attest_author":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE/action/author_attestation","sign_citation":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE/action/citation_signature","submit_replication":"https://pith.science/pith/HUQA63QUTPU2VRUOT3MOPZ3MNE/action/replication_record"}},"created_at":"2026-07-05T11:30:05.189124+00:00","updated_at":"2026-07-05T11:30:05.189124+00:00"}