{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E47LAHBFVAKUMP2E2WRWDH7FIB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b5ff4d86df169a83fd9d94ca937571cf717d90d94224eb86a2e078951c3fe12","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:18:27Z","title_canon_sha256":"e6735f287d8f9571e7a886e231c46bcebe4c98fe48455ae922825aff3fd8d088"},"schema_version":"1.0","source":{"id":"2602.10430","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.10430","created_at":"2026-07-29T01:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2602.10430v2","created_at":"2026-07-29T01:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10430","created_at":"2026-07-29T01:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"E47LAHBFVAKU","created_at":"2026-07-29T01:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"E47LAHBFVAKUMP2E","created_at":"2026-07-29T01:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"E47LAHBF","created_at":"2026-07-29T01:24:29Z"}],"graph_snapshots":[{"event_id":"sha256:f5d740a81f4e1c62029d358717ef660dbf11117cc19a7801df75be87b17495c4","target":"graph","created_at":"2026-07-29T01:24:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.10430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changping Wang, Jie Jiang, Jun Zhang, Yangru Huang, Yusen Huo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:18:27Z","title":"Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10430","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c6e459528511f8376a95953849e82c306e44c38570e5dceacefe000061bbd31","target":"record","created_at":"2026-07-29T01:24:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b5ff4d86df169a83fd9d94ca937571cf717d90d94224eb86a2e078951c3fe12","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T02:18:27Z","title_canon_sha256":"e6735f287d8f9571e7a886e231c46bcebe4c98fe48455ae922825aff3fd8d088"},"schema_version":"1.0","source":{"id":"2602.10430","kind":"arxiv","version":2}},"canonical_sha256":"273eb01c25a815463f44d5a3619fe54075cb11aa40fdfef9d11c1e080d5d90ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"273eb01c25a815463f44d5a3619fe54075cb11aa40fdfef9d11c1e080d5d90ce","first_computed_at":"2026-07-29T01:24:29.413533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:24:29.413533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xq8nGF4PAzxfsQAPZPsAVTnPt/i/FRi396Z8lQcyVHd0SRkFX8TphtVhpVvetJcE5q6LusaOZjaH1ipdJE4fDg==","signature_status":"signed_v1","signed_at":"2026-07-29T01:24:29.414470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.10430","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c6e459528511f8376a95953849e82c306e44c38570e5dceacefe000061bbd31","sha256:f5d740a81f4e1c62029d358717ef660dbf11117cc19a7801df75be87b17495c4"],"state_sha256":"2f3efe252e867e9e3360be174b84e2860d517fececfbc44333e5807b1fd47d45"}