{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NHBG2AQOXPN7Y4VWNQ343DKCNX","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":"b7753855282d365d6156b8b5954ba1befbd8e55e1864866ac875c8a00e3d5276","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T20:56:24Z","title_canon_sha256":"2ff345ae32e62a3b9a0754cf37939addd430a76387d9a7c0309cc41e1c6957f3"},"schema_version":"1.0","source":{"id":"2606.02884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02884","created_at":"2026-06-03T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02884v1","created_at":"2026-06-03T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02884","created_at":"2026-06-03T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"NHBG2AQOXPN7","created_at":"2026-06-03T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"NHBG2AQOXPN7Y4VW","created_at":"2026-06-03T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"NHBG2AQO","created_at":"2026-06-03T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:b9827d1670b846b2d5a89075f24e4bf4e5ee0e806c6948754e338fff87cbe643","target":"graph","created_at":"2026-06-03T01:05:25Z","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/2606.02884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time. While empirically powerful, these methods are prone to reward hacking: the guided model over-optimizes the reward at the cost of fidelity to the learned distribution. Prior work has attributed this to the complexity of neural reward functions or implicit biases in diffusion training, but its fundamental origins remain poorly understood. We show that reward hacking arises from an approximation made in most practical implementations of reward-guided diffusion -- finite-particle plug-","authors_text":"Nicholas M. Boffi, Sanjit Dandapanthula","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T20:56:24Z","title":"Are we really tilting? The mechanics of reward guidance in flow and diffusion models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02884","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:e3f58850bf20381cd151b89b59018fb0cb0dc0320e6da715380077fc4798819a","target":"record","created_at":"2026-06-03T01:05:25Z","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":"b7753855282d365d6156b8b5954ba1befbd8e55e1864866ac875c8a00e3d5276","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T20:56:24Z","title_canon_sha256":"2ff345ae32e62a3b9a0754cf37939addd430a76387d9a7c0309cc41e1c6957f3"},"schema_version":"1.0","source":{"id":"2606.02884","kind":"arxiv","version":1}},"canonical_sha256":"69c26d020ebbdbfc72b66c37cd8d426dd0031b507e70766d7f7884507b7fd58d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69c26d020ebbdbfc72b66c37cd8d426dd0031b507e70766d7f7884507b7fd58d","first_computed_at":"2026-06-03T01:05:25.679791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:25.679791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IHdaUyyD9os3Rl43mm49h7UjCPk0fWiHczxmVTrT1B2OvxGDP6y6Bq1M3YKdmx0jc2N9Zm9177ixc6AZ+YnyBA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:25.680178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3f58850bf20381cd151b89b59018fb0cb0dc0320e6da715380077fc4798819a","sha256:b9827d1670b846b2d5a89075f24e4bf4e5ee0e806c6948754e338fff87cbe643"],"state_sha256":"4bbbeb2a1c18465ebfb4e41c62063600c9aebb606ea2be5e6eeb10912d96b2f1"}