{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KDRU4PGUFSX2YOI3HSHBL7ZGOJ","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":"834a20599dc52c7d9aa43df9e3a89daad5ce566f01d2298f71e6a1976310f102","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-19T14:10:38Z","title_canon_sha256":"b7b5b7f5f1dabec95e8c4298f225f2ec93ee6c140fdad49f7cfd60e55ed8cba5"},"schema_version":"1.0","source":{"id":"2409.12799","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12799","created_at":"2026-07-05T10:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12799v3","created_at":"2026-07-05T10:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12799","created_at":"2026-07-05T10:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"KDRU4PGUFSX2","created_at":"2026-07-05T10:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"KDRU4PGUFSX2YOI3","created_at":"2026-07-05T10:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"KDRU4PGU","created_at":"2026-07-05T10:44:16Z"}],"graph_snapshots":[{"event_id":"sha256:9b8fc9caf9e801da919a1880f84fada25bc83612cf656be4ff7f54264aab23a3","target":"graph","created_at":"2026-07-05T10:44:16Z","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/2409.12799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper illustrates the central role of loss functions in data-driven decision making, providing a comprehensive survey on their influence in cost-sensitive classification (CSC) and reinforcement learning (RL). We demonstrate how different regression loss functions affect the sample efficiency and adaptivity of value-based decision making algorithms. Across multiple settings, we prove that algorithms using the binary cross-entropy loss achieve first-order bounds scaling with the optimal policy's cost and are much more efficient than the commonly used squared loss. Moreover, we prove that di","authors_text":"Kaiwen Wang, Nathan Kallus, Wen Sun","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-19T14:10:38Z","title":"The Central Role of the Loss Function in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12799","kind":"arxiv","version":3},"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":"sha256:6acf8a90df3391af1961024aab1ab45fd5caa68823264fb71883236f1e5cd475","target":"record","created_at":"2026-07-05T10:44:16Z","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":"834a20599dc52c7d9aa43df9e3a89daad5ce566f01d2298f71e6a1976310f102","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-19T14:10:38Z","title_canon_sha256":"b7b5b7f5f1dabec95e8c4298f225f2ec93ee6c140fdad49f7cfd60e55ed8cba5"},"schema_version":"1.0","source":{"id":"2409.12799","kind":"arxiv","version":3}},"canonical_sha256":"50e34e3cd42cafac391b3c8e15ff26724a7f8c8153a3168b61783c12084855e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50e34e3cd42cafac391b3c8e15ff26724a7f8c8153a3168b61783c12084855e3","first_computed_at":"2026-07-05T10:44:16.501741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:16.501741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3PkTWpyPT9jepoVp4zTj0GfzoPxb3zeNu/A+X9d3t+o6ElQLTgGVmhtfD8BlsdhJXq2VWQzfjTUFMm5tIqnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:16.502238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12799","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6acf8a90df3391af1961024aab1ab45fd5caa68823264fb71883236f1e5cd475","sha256:9b8fc9caf9e801da919a1880f84fada25bc83612cf656be4ff7f54264aab23a3"],"state_sha256":"0f5ec077feaf1327b730bc85b4fb4c0155dcf53a43d4705281279de31b4b9aa0"}