{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EJBZHNIFA7RDHSWIYE22OQ6AD4","short_pith_number":"pith:EJBZHNIF","schema_version":"1.0","canonical_sha256":"224393b50507e233cac8c135a743c01f33f4fb5bf5f2e783163593496b721c33","source":{"kind":"arxiv","id":"2607.17326","version":1},"attestation_state":"computed","paper":{"title":"Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Naik, A. Rupam Mahmood, Colin Bellinger, Hany Hamed","submitted_at":"2026-07-19T16:29:13Z","abstract_excerpt":"Transfer-oriented reinforcement learning requires evaluating algorithms along dimensions that go beyond standard sample efficiency. We focus on two dimensions: practical efficiency, which asks whether conclusions about algorithm suitability change under wall-clock rather than interaction-based budgets, and robustness under dynamics mismatch, which asks how different learning paradigms respond to variability in the training distribution induced by domain randomization. We provide two insights to reinforcement-learning practitioners. First, comparing the sample efficiency of different algorithms"},"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":"2607.17326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T16:29:13Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b143aba082f19ff32b7c13226a653c1b1183811618b83ac82c1e7caaf2170774","abstract_canon_sha256":"20170b0131998a9039df002b1c06f3ff668d51f96dada286378d08d1fafdda3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:27.426176Z","signature_b64":"O1cVXySSeoN2+7h1SIJbGBlLmfMMHjkBs2E9T2+qBJ7Qo03mD0dQhXdo0yq/YlY/7dftGCtcdlU7wF7ITK5iBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"224393b50507e233cac8c135a743c01f33f4fb5bf5f2e783163593496b721c33","last_reissued_at":"2026-07-21T01:21:27.425336Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:27.425336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Naik, A. Rupam Mahmood, Colin Bellinger, Hany Hamed","submitted_at":"2026-07-19T16:29:13Z","abstract_excerpt":"Transfer-oriented reinforcement learning requires evaluating algorithms along dimensions that go beyond standard sample efficiency. We focus on two dimensions: practical efficiency, which asks whether conclusions about algorithm suitability change under wall-clock rather than interaction-based budgets, and robustness under dynamics mismatch, which asks how different learning paradigms respond to variability in the training distribution induced by domain randomization. We provide two insights to reinforcement-learning practitioners. First, comparing the sample efficiency of different algorithms"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17326","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/2607.17326/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":"2607.17326","created_at":"2026-07-21T01:21:27.425767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17326v1","created_at":"2026-07-21T01:21:27.425767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17326","created_at":"2026-07-21T01:21:27.425767+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJBZHNIFA7RD","created_at":"2026-07-21T01:21:27.425767+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJBZHNIFA7RDHSWI","created_at":"2026-07-21T01:21:27.425767+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJBZHNIF","created_at":"2026-07-21T01:21:27.425767+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/EJBZHNIFA7RDHSWIYE22OQ6AD4","json":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4.json","graph_json":"https://pith.science/api/pith-number/EJBZHNIFA7RDHSWIYE22OQ6AD4/graph.json","events_json":"https://pith.science/api/pith-number/EJBZHNIFA7RDHSWIYE22OQ6AD4/events.json","paper":"https://pith.science/paper/EJBZHNIF"},"agent_actions":{"view_html":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4","download_json":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4.json","view_paper":"https://pith.science/paper/EJBZHNIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17326&json=true","fetch_graph":"https://pith.science/api/pith-number/EJBZHNIFA7RDHSWIYE22OQ6AD4/graph.json","fetch_events":"https://pith.science/api/pith-number/EJBZHNIFA7RDHSWIYE22OQ6AD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4/action/storage_attestation","attest_author":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4/action/author_attestation","sign_citation":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4/action/citation_signature","submit_replication":"https://pith.science/pith/EJBZHNIFA7RDHSWIYE22OQ6AD4/action/replication_record"}},"created_at":"2026-07-21T01:21:27.425767+00:00","updated_at":"2026-07-21T01:21:27.425767+00:00"}