{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UJD6C5LKM6FET57BR5S427227D","short_pith_number":"pith:UJD6C5LK","schema_version":"1.0","canonical_sha256":"a247e1756a678a49f7e18f65cd7f5af8e8ff466fe8f75a884968938cd2b826da","source":{"kind":"arxiv","id":"2605.05863","version":2},"attestation_state":"computed","paper":{"title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"SOPE uses an actor-aligned OPE signal on held-out data to automatically stop offline phases in online RL with prior data.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Sestini, Andrew D. Bagdanov, Carlo Romeo, Girolamo Macaluso","submitted_at":"2026-05-07T08:32:09Z","abstract_excerpt":"Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases are significantly more computationally efficient than static update schedules, they require task-dependent manual tuning, risking either the waste of prior knowledge or severe overfitting. To address this, we propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation (OPE) signal as an automated early-stopping mechanism to dynamically "},"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":"2605.05863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T08:32:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"385fe671c4fa7b2102bd48a27a22b37a07480575b6974d319ac81587ec48f3c2","abstract_canon_sha256":"c9929fbe9928ffdf20365251fc61cf2891f678711bc7705ee68bedcdf8189391"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:20.300587Z","signature_b64":"JH0r353m5FZtVyMpsR4mhtDk87FLbw0AaipGs9t+0EozVJk8zFfrtetWjHzXZPIlpNDfP2VwX3wGGwnNi/7tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a247e1756a678a49f7e18f65cd7f5af8e8ff466fe8f75a884968938cd2b826da","last_reissued_at":"2026-05-21T01:05:20.299992Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:20.299992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"SOPE uses an actor-aligned OPE signal on held-out data to automatically stop offline phases in online RL with prior data.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Sestini, Andrew D. Bagdanov, Carlo Romeo, Girolamo Macaluso","submitted_at":"2026-05-07T08:32:09Z","abstract_excerpt":"Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases are significantly more computationally efficient than static update schedules, they require task-dependent manual tuning, risking either the waste of prior knowledge or severe overfitting. To address this, we propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation (OPE) signal as an automated early-stopping mechanism to dynamically "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluated on 25 continuous control tasks from the Minari benchmark suite, SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x, thus balancing the tradeoff between sample and computational efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the actor-aligned OPE signal evaluated on a held-out validation split under the current policy's action distribution accurately detects the saturation point of out-of-distribution benefits without either stopping too early (wasting prior knowledge) or too late (causing overfitting).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SOPE uses an actor-aligned OPE signal on a held-out validation split to dynamically stop offline stabilization phases in online RL, improving performance up to 45.6% and cutting TFLOPs up to 22x on 25 Minari tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SOPE uses an actor-aligned OPE signal on held-out data to automatically stop offline phases in online RL with prior data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d9f3a58267f272a031f4a8ec3df5db7e734dda18b4f217eba9b3e2c990741e3"},"source":{"id":"2605.05863","kind":"arxiv","version":2},"verdict":{"id":"cbbfe96c-6794-43dd-8ec4-ae751b735dc1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T14:50:37.993640Z","strongest_claim":"Evaluated on 25 continuous control tasks from the Minari benchmark suite, SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x, thus balancing the tradeoff between sample and computational efficiency.","one_line_summary":"SOPE uses an actor-aligned OPE signal on a held-out validation split to dynamically stop offline stabilization phases in online RL, improving performance up to 45.6% and cutting TFLOPs up to 22x on 25 Minari tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the actor-aligned OPE signal evaluated on a held-out validation split under the current policy's action distribution accurately detects the saturation point of out-of-distribution benefits without either stopping too early (wasting prior knowledge) or too late (causing overfitting).","pith_extraction_headline":"SOPE uses an actor-aligned OPE signal on held-out data to automatically stop offline phases in online RL with prior data."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05863/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T13:42:04.568842Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T08:41:37.757500Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T19:31:19.547150Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:10:19.048833Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b18319b5272c7d5c096da65596b096e7694a12c061693846f15a8f159d8db496"},"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":"2605.05863","created_at":"2026-05-21T01:05:20.300072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.05863v2","created_at":"2026-05-21T01:05:20.300072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05863","created_at":"2026-05-21T01:05:20.300072+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJD6C5LKM6FE","created_at":"2026-05-21T01:05:20.300072+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJD6C5LKM6FET57B","created_at":"2026-05-21T01:05:20.300072+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJD6C5LK","created_at":"2026-05-21T01:05:20.300072+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/UJD6C5LKM6FET57BR5S427227D","json":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D.json","graph_json":"https://pith.science/api/pith-number/UJD6C5LKM6FET57BR5S427227D/graph.json","events_json":"https://pith.science/api/pith-number/UJD6C5LKM6FET57BR5S427227D/events.json","paper":"https://pith.science/paper/UJD6C5LK"},"agent_actions":{"view_html":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D","download_json":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D.json","view_paper":"https://pith.science/paper/UJD6C5LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.05863&json=true","fetch_graph":"https://pith.science/api/pith-number/UJD6C5LKM6FET57BR5S427227D/graph.json","fetch_events":"https://pith.science/api/pith-number/UJD6C5LKM6FET57BR5S427227D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D/action/storage_attestation","attest_author":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D/action/author_attestation","sign_citation":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D/action/citation_signature","submit_replication":"https://pith.science/pith/UJD6C5LKM6FET57BR5S427227D/action/replication_record"}},"created_at":"2026-05-21T01:05:20.300072+00:00","updated_at":"2026-05-21T01:05:20.300072+00:00"}