{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RATLW43PTSEQPIGVIBSF25YIDS","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":"0883d9fb49390784a975772bc6c17f874d362e8353e9eb17a97176222a0edb3e","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:30:24Z","title_canon_sha256":"2309bbcd7782cf999aea46844c3f2d2368396539e81c829f7458576bc804bbd1"},"schema_version":"1.0","source":{"id":"2606.23640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23640","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23640v1","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23640","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"RATLW43PTSEQ","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"RATLW43PTSEQPIGV","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"RATLW43P","created_at":"2026-06-23T03:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:d42cbbf34c78b4be320954fc07c1d11c5a697ef990248e6bbbce0040da8700cc","target":"graph","created_at":"2026-06-23T03:14:33Z","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/2606.23640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many modern applications of reinforcement learning (RL), the natural reward for a task of interest is inherently sparse: a reward of 0 is given everywhere except when the task is completed, when a reward of +1 is given. Training a policy to maximize such a sparse reward requires solving a challenging credit assignment problem, leading to slow or ineffective RL improvement. We propose a simple approach to transform a sparse outcome reward into a dense process reward. Our approach relies on training a discriminator to distinguish between previous successful and unsuccessful episodes, and usin","authors_text":"Andrew Wagenmaker, Raymond Tsao, Sergey Levine","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:30:24Z","title":"Learning Process Rewards via Success Visitation Matching for Efficient RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23640","kind":"arxiv","version":1},"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":"sha256:7f76c48c5be1c8c1cdd5e0d1ca41158497bc8b27e3845d26fa41632d6473860c","target":"record","created_at":"2026-06-23T03:14:33Z","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":"0883d9fb49390784a975772bc6c17f874d362e8353e9eb17a97176222a0edb3e","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:30:24Z","title_canon_sha256":"2309bbcd7782cf999aea46844c3f2d2368396539e81c829f7458576bc804bbd1"},"schema_version":"1.0","source":{"id":"2606.23640","kind":"arxiv","version":1}},"canonical_sha256":"8826bb736f9c8907a0d540645d77081c83a0607e8443599c661f9ffb2625b363","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8826bb736f9c8907a0d540645d77081c83a0607e8443599c661f9ffb2625b363","first_computed_at":"2026-06-23T03:14:33.053179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:33.053179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GQnPBh/AnJI8qXRei7mBXGuhgN0rYm6nX0jRwH8Q3PNWDa5ax/F+sffn75R6KvBQ9skp0A0Nc7OHTeI5ZgI+Ag==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:33.053605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f76c48c5be1c8c1cdd5e0d1ca41158497bc8b27e3845d26fa41632d6473860c","sha256:d42cbbf34c78b4be320954fc07c1d11c5a697ef990248e6bbbce0040da8700cc"],"state_sha256":"70b3b691347593ca7bef52f4f381a17c0053605996fc06ed3f6ba3fb5d092ddd"}