{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BWSIXPTCUWQESIEGFZIORUC3N3","short_pith_number":"pith:BWSIXPTC","canonical_record":{"source":{"id":"2508.00174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T21:39:24Z","cross_cats_sorted":[],"title_canon_sha256":"4f7ad7676668a19f2d99d28bf46d2477b629f3943bab67f3d61dcdd85e34c106","abstract_canon_sha256":"13009d13a8dfc2dc59b48dc58746c993cb620928f26887a0dcd01b30fa12e766"},"schema_version":"1.0"},"canonical_sha256":"0da48bbe62a5a04920862e50e8d05b6eca570e9df6aec7de6887648888de4e86","source":{"kind":"arxiv","id":"2508.00174","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00174","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00174v1","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00174","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"BWSIXPTCUWQE","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"BWSIXPTCUWQESIEG","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"BWSIXPTC","created_at":"2026-07-05T11:46:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BWSIXPTCUWQESIEGFZIORUC3N3","target":"record","payload":{"canonical_record":{"source":{"id":"2508.00174","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T21:39:24Z","cross_cats_sorted":[],"title_canon_sha256":"4f7ad7676668a19f2d99d28bf46d2477b629f3943bab67f3d61dcdd85e34c106","abstract_canon_sha256":"13009d13a8dfc2dc59b48dc58746c993cb620928f26887a0dcd01b30fa12e766"},"schema_version":"1.0"},"canonical_sha256":"0da48bbe62a5a04920862e50e8d05b6eca570e9df6aec7de6887648888de4e86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:50.367136Z","signature_b64":"Su9+A4+5icu2NclnKS10cKwXbtx90GY/JAVIAfHzUZ70ZhpokyAZedRZPG2MaPzGbErcjv6jZkkXVIHy/FghBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0da48bbe62a5a04920862e50e8d05b6eca570e9df6aec7de6887648888de4e86","last_reissued_at":"2026-07-05T11:46:50.366648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:50.366648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.00174","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyIWWkYGjsmfDMzswKeGszgFb79Bwk9yIez7IejGm51ZPoRmv0GySfuESMBrYmbHSJ/Yhw7GAWvmV/Oy4ujTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:08:41.409848Z"},"content_sha256":"69bdc220c1de97889ab056de6dfb00e197220c97e9d34329a60579ebc8091f81","schema_version":"1.0","event_id":"sha256:69bdc220c1de97889ab056de6dfb00e197220c97e9d34329a60579ebc8091f81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BWSIXPTCUWQESIEGFZIORUC3N3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL as Regressor: A Reinforcement Learning Approach for Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yongchao Huang","submitted_at":"2025-07-31T21:39:24Z","abstract_excerpt":"Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing with asymmetric costs or complex, non-differentiable objectives. In this paper, we explore an alternative paradigm: framing regression as a Reinforcement Learning (RL) problem. We demonstrate this by treating a model's prediction as an action and defining a custom reward signal based on the prediction error, and we can leverage powerful RL algorithms to perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00174","kind":"arxiv","version":1},"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/2508.00174/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":"2026-07-05T11:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDol6vFYcm34PxlqnsaqE3WoiSNSWIXzNMrsZuGJ7KLDdveRJ6zjAVAsehihOb6zC2lsx8Uwe9ui+Hxoh5ElDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:08:41.410353Z"},"content_sha256":"9737bdc22721827af7be8f452a21b4b4c9975ff563a8d82aaecea85fdecac61a","schema_version":"1.0","event_id":"sha256:9737bdc22721827af7be8f452a21b4b4c9975ff563a8d82aaecea85fdecac61a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BWSIXPTCUWQESIEGFZIORUC3N3/bundle.json","state_url":"https://pith.science/pith/BWSIXPTCUWQESIEGFZIORUC3N3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BWSIXPTCUWQESIEGFZIORUC3N3/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":"2026-08-08T05:08:41Z","links":{"resolver":"https://pith.science/pith/BWSIXPTCUWQESIEGFZIORUC3N3","bundle":"https://pith.science/pith/BWSIXPTCUWQESIEGFZIORUC3N3/bundle.json","state":"https://pith.science/pith/BWSIXPTCUWQESIEGFZIORUC3N3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BWSIXPTCUWQESIEGFZIORUC3N3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BWSIXPTCUWQESIEGFZIORUC3N3","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":"13009d13a8dfc2dc59b48dc58746c993cb620928f26887a0dcd01b30fa12e766","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T21:39:24Z","title_canon_sha256":"4f7ad7676668a19f2d99d28bf46d2477b629f3943bab67f3d61dcdd85e34c106"},"schema_version":"1.0","source":{"id":"2508.00174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00174","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00174v1","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00174","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"BWSIXPTCUWQE","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"BWSIXPTCUWQESIEG","created_at":"2026-07-05T11:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"BWSIXPTC","created_at":"2026-07-05T11:46:50Z"}],"graph_snapshots":[{"event_id":"sha256:9737bdc22721827af7be8f452a21b4b4c9975ff563a8d82aaecea85fdecac61a","target":"graph","created_at":"2026-07-05T11:46:50Z","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/2508.00174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing with asymmetric costs or complex, non-differentiable objectives. In this paper, we explore an alternative paradigm: framing regression as a Reinforcement Learning (RL) problem. We demonstrate this by treating a model's prediction as an action and defining a custom reward signal based on the prediction error, and we can leverage powerful RL algorithms to perfo","authors_text":"Yongchao Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T21:39:24Z","title":"RL as Regressor: A Reinforcement Learning Approach for Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00174","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":"sha256:69bdc220c1de97889ab056de6dfb00e197220c97e9d34329a60579ebc8091f81","target":"record","created_at":"2026-07-05T11:46:50Z","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":"13009d13a8dfc2dc59b48dc58746c993cb620928f26887a0dcd01b30fa12e766","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T21:39:24Z","title_canon_sha256":"4f7ad7676668a19f2d99d28bf46d2477b629f3943bab67f3d61dcdd85e34c106"},"schema_version":"1.0","source":{"id":"2508.00174","kind":"arxiv","version":1}},"canonical_sha256":"0da48bbe62a5a04920862e50e8d05b6eca570e9df6aec7de6887648888de4e86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0da48bbe62a5a04920862e50e8d05b6eca570e9df6aec7de6887648888de4e86","first_computed_at":"2026-07-05T11:46:50.366648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:50.366648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Su9+A4+5icu2NclnKS10cKwXbtx90GY/JAVIAfHzUZ70ZhpokyAZedRZPG2MaPzGbErcjv6jZkkXVIHy/FghBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:50.367136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69bdc220c1de97889ab056de6dfb00e197220c97e9d34329a60579ebc8091f81","sha256:9737bdc22721827af7be8f452a21b4b4c9975ff563a8d82aaecea85fdecac61a"],"state_sha256":"f7671ff6a9c50e85b26efdde0a0d1fb46bb65658fe355947f9ac943420766079"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KY+jF6YI/x8k65nAwQEwWJEyvsHzB4pWsiv8u2G1ezfMuhnSrU7/4PJVySGRrgSiJIV7wKicCGGJKSX/VwQTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:08:41.415263Z","bundle_sha256":"4e831a21d0f31c4ade7403f8ae0fbc50dff573863657fb05cc8e996e77dcb29f"}}