{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E47LAHBFVAKUMP2E2WRWDH7FIB","short_pith_number":"pith:E47LAHBF","schema_version":"1.0","canonical_sha256":"273eb01c25a815463f44d5a3619fe54075cb11aa40fdfef9d11c1e080d5d90ce","source":{"kind":"arxiv","id":"2602.10430","version":2},"attestation_state":"computed","paper":{"title":"Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changping Wang, Jie Jiang, Jun Zhang, Yangru Huang, Yusen Huo","submitted_at":"2026-02-11T02:18:27Z","abstract_excerpt":"Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that repeated reuse can turn this useful signal into excessive repulsion: as the learner moves away from a historical negative action, subsequent updates make that action increasingly remote without necessarily reducing its update strength. Our aggregate theory characterizes the resulting transition from a stable displacement beyond the positive-only target to persistent drift and the loss of finite stable equilibria; controlled strength sweeps show that an inte"},"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":"2602.10430","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:18:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e6735f287d8f9571e7a886e231c46bcebe4c98fe48455ae922825aff3fd8d088","abstract_canon_sha256":"0b5ff4d86df169a83fd9d94ca937571cf717d90d94224eb86a2e078951c3fe12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:24:29.414470Z","signature_b64":"Xq8nGF4PAzxfsQAPZPsAVTnPt/i/FRi396Z8lQcyVHd0SRkFX8TphtVhpVvetJcE5q6LusaOZjaH1ipdJE4fDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"273eb01c25a815463f44d5a3619fe54075cb11aa40fdfef9d11c1e080d5d90ce","last_reissued_at":"2026-07-29T01:24:29.413533Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:24:29.413533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changping Wang, Jie Jiang, Jun Zhang, Yangru Huang, Yusen Huo","submitted_at":"2026-02-11T02:18:27Z","abstract_excerpt":"Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that repeated reuse can turn this useful signal into excessive repulsion: as the learner moves away from a historical negative action, subsequent updates make that action increasingly remote without necessarily reducing its update strength. Our aggregate theory characterizes the resulting transition from a stable displacement beyond the positive-only target to persistent drift and the loss of finite stable equilibria; controlled strength sweeps show that an inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10430","kind":"arxiv","version":2},"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/2602.10430/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":"2602.10430","created_at":"2026-07-29T01:24:29.413951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10430v2","created_at":"2026-07-29T01:24:29.413951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10430","created_at":"2026-07-29T01:24:29.413951+00:00"},{"alias_kind":"pith_short_12","alias_value":"E47LAHBFVAKU","created_at":"2026-07-29T01:24:29.413951+00:00"},{"alias_kind":"pith_short_16","alias_value":"E47LAHBFVAKUMP2E","created_at":"2026-07-29T01:24:29.413951+00:00"},{"alias_kind":"pith_short_8","alias_value":"E47LAHBF","created_at":"2026-07-29T01:24:29.413951+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/E47LAHBFVAKUMP2E2WRWDH7FIB","json":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB.json","graph_json":"https://pith.science/api/pith-number/E47LAHBFVAKUMP2E2WRWDH7FIB/graph.json","events_json":"https://pith.science/api/pith-number/E47LAHBFVAKUMP2E2WRWDH7FIB/events.json","paper":"https://pith.science/paper/E47LAHBF"},"agent_actions":{"view_html":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB","download_json":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB.json","view_paper":"https://pith.science/paper/E47LAHBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10430&json=true","fetch_graph":"https://pith.science/api/pith-number/E47LAHBFVAKUMP2E2WRWDH7FIB/graph.json","fetch_events":"https://pith.science/api/pith-number/E47LAHBFVAKUMP2E2WRWDH7FIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB/action/storage_attestation","attest_author":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB/action/author_attestation","sign_citation":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB/action/citation_signature","submit_replication":"https://pith.science/pith/E47LAHBFVAKUMP2E2WRWDH7FIB/action/replication_record"}},"created_at":"2026-07-29T01:24:29.413951+00:00","updated_at":"2026-07-29T01:24:29.413951+00:00"}