{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KDRU4PGUFSX2YOI3HSHBL7ZGOJ","short_pith_number":"pith:KDRU4PGU","canonical_record":{"source":{"id":"2409.12799","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-19T14:10:38Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"b7b5b7f5f1dabec95e8c4298f225f2ec93ee6c140fdad49f7cfd60e55ed8cba5","abstract_canon_sha256":"834a20599dc52c7d9aa43df9e3a89daad5ce566f01d2298f71e6a1976310f102"},"schema_version":"1.0"},"canonical_sha256":"50e34e3cd42cafac391b3c8e15ff26724a7f8c8153a3168b61783c12084855e3","source":{"kind":"arxiv","id":"2409.12799","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KDRU4PGUFSX2YOI3HSHBL7ZGOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12799","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-19T14:10:38Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"b7b5b7f5f1dabec95e8c4298f225f2ec93ee6c140fdad49f7cfd60e55ed8cba5","abstract_canon_sha256":"834a20599dc52c7d9aa43df9e3a89daad5ce566f01d2298f71e6a1976310f102"},"schema_version":"1.0"},"canonical_sha256":"50e34e3cd42cafac391b3c8e15ff26724a7f8c8153a3168b61783c12084855e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:16.502238Z","signature_b64":"S3PkTWpyPT9jepoVp4zTj0GfzoPxb3zeNu/A+X9d3t+o6ElQLTgGVmhtfD8BlsdhJXq2VWQzfjTUFMm5tIqnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50e34e3cd42cafac391b3c8e15ff26724a7f8c8153a3168b61783c12084855e3","last_reissued_at":"2026-07-05T10:44:16.501741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:16.501741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12799","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtWDFfILIK3bYl26ObZTZpxfIwNWMgGANwX/yH4/NZQ+CS4O62C+dzJV6rVap1GzZG4bbq/SJ1HH61SLh8qsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:35:35.696107Z"},"content_sha256":"6acf8a90df3391af1961024aab1ab45fd5caa68823264fb71883236f1e5cd475","schema_version":"1.0","event_id":"sha256:6acf8a90df3391af1961024aab1ab45fd5caa68823264fb71883236f1e5cd475"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KDRU4PGUFSX2YOI3HSHBL7ZGOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Central Role of the Loss Function in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Kaiwen Wang, Nathan Kallus, Wen Sun","submitted_at":"2024-09-19T14:10:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12799","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.12799/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0EuIzzE7WqFtr92Nvmc4YACiT3p3HRVP/qLr1VUq5pql4oqjprSIl1RYwOcFTN4oxa9OW1JxJF55hnTUaD10DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:35:35.696635Z"},"content_sha256":"9b8fc9caf9e801da919a1880f84fada25bc83612cf656be4ff7f54264aab23a3","schema_version":"1.0","event_id":"sha256:9b8fc9caf9e801da919a1880f84fada25bc83612cf656be4ff7f54264aab23a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ/bundle.json","state_url":"https://pith.science/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T06:35:35Z","links":{"resolver":"https://pith.science/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ","bundle":"https://pith.science/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ/bundle.json","state":"https://pith.science/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDRU4PGUFSX2YOI3HSHBL7ZGOJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+9Cri98u03/gxb6mN8cuJ0zxKffWf2fZ8sHR7b8YDXophyVwLsknkwWrx8toGqgTPFdQuNgKwBxzuO+M52NAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:35:35.701170Z","bundle_sha256":"ec6d79095992f44cabea17f0fd4972b32f2ca6403a41b9cd8c923c3b905c583c"}}