{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:234655NSQRHZNB6UP3E4LXOTCE","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":"680e58ddb499a738e11c89b3aeccdc20a3416ada1a14e0f2a011a9e3674dd0f0","cross_cats_sorted":["cs.GL","cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-04T16:29:38Z","title_canon_sha256":"8d49b69f627d69caa8c74009d02abb92666de4e722160c95929e539fb3baa3f2"},"schema_version":"1.0","source":{"id":"2509.04372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04372","created_at":"2026-07-05T12:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04372v1","created_at":"2026-07-05T12:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04372","created_at":"2026-07-05T12:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"234655NSQRHZ","created_at":"2026-07-05T12:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"234655NSQRHZNB6U","created_at":"2026-07-05T12:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"234655NS","created_at":"2026-07-05T12:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:75ac9375bddebec715e242e0137cfba183297110d070e8bf135edf740fef1122","target":"graph","created_at":"2026-07-05T12:04:58Z","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/2509.04372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this note, we reflect on several fundamental connections among widely used post-training techniques. We clarify some intimate connections and equivalences between reinforcement learning with human feedback, reinforcement learning with internal feedback, and test-time scaling (particularly soft best-of-$N$ sampling), while also illuminating intrinsic links between diffusion guidance and test-time scaling. Additionally, we introduce a resampling approach for alignment and reward-directed diffusion models, sidestepping the need for explicit reinforcement learning techniques.","authors_text":"Gen Li, Yuchen Jiao, Yuxin Chen","cross_cats":["cs.GL","cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-04T16:29:38Z","title":"Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04372","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":"sha256:539348191698f4ff91af7dcfad0eafa7eaca81074cbed01192f2b37a68fbafe2","target":"record","created_at":"2026-07-05T12:04:58Z","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":"680e58ddb499a738e11c89b3aeccdc20a3416ada1a14e0f2a011a9e3674dd0f0","cross_cats_sorted":["cs.GL","cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-04T16:29:38Z","title_canon_sha256":"8d49b69f627d69caa8c74009d02abb92666de4e722160c95929e539fb3baa3f2"},"schema_version":"1.0","source":{"id":"2509.04372","kind":"arxiv","version":1}},"canonical_sha256":"d6f9eef5b2844f9687d47ec9c5ddd31134f1da8f2977c6af26e1a6cda6133008","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6f9eef5b2844f9687d47ec9c5ddd31134f1da8f2977c6af26e1a6cda6133008","first_computed_at":"2026-07-05T12:04:58.469551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:58.469551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zyw9xdGdPZYXWuUgfYsia+iE2Z9X6WLHYYYzcf7GyZAcEiJ+3eh2t+LX+AAoPnZu5e8UZ2srarOokNdADFORDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:58.470109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:539348191698f4ff91af7dcfad0eafa7eaca81074cbed01192f2b37a68fbafe2","sha256:75ac9375bddebec715e242e0137cfba183297110d070e8bf135edf740fef1122"],"state_sha256":"16fcb15de5b7fe8d68bda7799e14f30eb1990b8ddae9f9657519a0be48c2e642"}