{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HY7URAXVX33PYOLVLI3IOLVCS2","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":"bb20732a5668eb5e64eca1a14dd73310b8a16d88f9e38e53c6f797ac3cfcee3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T18:48:39Z","title_canon_sha256":"1af7f9cbb3b12605f3110525a380b8b1fc2dd89e6c1b1bcc817379d399be7b94"},"schema_version":"1.0","source":{"id":"2608.00816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00816","created_at":"2026-08-04T01:55:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00816v1","created_at":"2026-08-04T01:55:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00816","created_at":"2026-08-04T01:55:11Z"},{"alias_kind":"pith_short_12","alias_value":"HY7URAXVX33P","created_at":"2026-08-04T01:55:11Z"},{"alias_kind":"pith_short_16","alias_value":"HY7URAXVX33PYOLV","created_at":"2026-08-04T01:55:11Z"},{"alias_kind":"pith_short_8","alias_value":"HY7URAXV","created_at":"2026-08-04T01:55:11Z"}],"graph_snapshots":[{"event_id":"sha256:b96fbbac2b90b831173bdf8d14825f40021d251ced31e8f8d6caa8c40b33779d","target":"graph","created_at":"2026-08-04T01:55:11Z","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/2608.00816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recommendation systems, users interact with only a small fraction of a vast item catalog, producing feedback that is both sparse and noisy. This challenges post-training generative recommenders: reward models trained from logged interactions often fail to generalize, while directly optimizing imperfect rewards can lead to reward over-optimization. We propose Exponential reward-weighted fine-tuning (Exp-RSFT), where each logged interaction is weighted by $\\exp(r/\\lambda)$, avoids this failure by optimizing directly on the logged rewards, with the temperature $\\lambda$ regularizing against th","authors_text":"Keertana Chidambaram, Ko-Jen Hsiao, Moumita Bhattacharya, Qiuling Xu, Sanath Kumar Krishnamurthy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T18:48:39Z","title":"Exponential Reward Weighting for Fine-Tuning Generative Recommenders under Sparse and Noisy Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00816","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:b5c23d2bf80ea514183a754029e9a98a024f40d3c041621295c37da072b5b356","target":"record","created_at":"2026-08-04T01:55:11Z","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":"bb20732a5668eb5e64eca1a14dd73310b8a16d88f9e38e53c6f797ac3cfcee3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T18:48:39Z","title_canon_sha256":"1af7f9cbb3b12605f3110525a380b8b1fc2dd89e6c1b1bcc817379d399be7b94"},"schema_version":"1.0","source":{"id":"2608.00816","kind":"arxiv","version":1}},"canonical_sha256":"3e3f4882f5bef6fc39755a36872ea29688a7f82ce947ec97e77d3476e01b7035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e3f4882f5bef6fc39755a36872ea29688a7f82ce947ec97e77d3476e01b7035","first_computed_at":"2026-08-04T01:55:11.861765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:55:11.861765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HjwG1Z3E/Ffn7Q8j2wlBjFl8AkoyixxeRcOL4thdUuzqjOVUJVM/SkeuhkBA237nCnNusYy95XQBzZGUIWVeBA==","signature_status":"signed_v1","signed_at":"2026-08-04T01:55:11.863382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5c23d2bf80ea514183a754029e9a98a024f40d3c041621295c37da072b5b356","sha256:b96fbbac2b90b831173bdf8d14825f40021d251ced31e8f8d6caa8c40b33779d"],"state_sha256":"66484892270e7d0c6d73a5ea3d9b982db3d24607e25a293de1a56803b9ae7166"}