{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NWOU6MHM4KCGCBFEW7PW5762CI","short_pith_number":"pith:NWOU6MHM","canonical_record":{"source":{"id":"2605.20740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:43:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff1bb9af79ccceca54bef0eedfb7c3fe03f639d94b4ca3705c921b0b6584fff7","abstract_canon_sha256":"ca0aa2e60ef6d78088f20b42d4c67eb0b5839af53ed2cd83cc898654195cda16"},"schema_version":"1.0"},"canonical_sha256":"6d9d4f30ece2846104a4b7df6effda12209e95fb3c14a7f868d4e338e7a01edc","source":{"kind":"arxiv","id":"2605.20740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20740","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20740v1","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20740","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"NWOU6MHM4KCG","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"NWOU6MHM4KCGCBFE","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"NWOU6MHM","created_at":"2026-05-21T01:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NWOU6MHM4KCGCBFEW7PW5762CI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:43:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff1bb9af79ccceca54bef0eedfb7c3fe03f639d94b4ca3705c921b0b6584fff7","abstract_canon_sha256":"ca0aa2e60ef6d78088f20b42d4c67eb0b5839af53ed2cd83cc898654195cda16"},"schema_version":"1.0"},"canonical_sha256":"6d9d4f30ece2846104a4b7df6effda12209e95fb3c14a7f868d4e338e7a01edc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:51.672487Z","signature_b64":"yQulVuV+ZLc6JspOj0yTlwbelwrRiVQbRVEgkAKuXfhLKBosxs9/4gD1eAq3xqKTKeXPgd7lUxUxDjfcdjNMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d9d4f30ece2846104a4b7df6effda12209e95fb3c14a7f868d4e338e7a01edc","last_reissued_at":"2026-05-21T01:04:51.671849Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:51.671849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20740","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":"2026-05-21T01:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g0OAbZr+lE9tHY4LJNuQU7y4ZLF/ygAfkYpowOj78o94k8m+GidGczV5+uO6Nw0503iDaf6/TqT/exqdzhTlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:47:23.571925Z"},"content_sha256":"a762d5678784960ec7dce252f88cf94d14976d8010411d037c2873debab116e6","schema_version":"1.0","event_id":"sha256:a762d5678784960ec7dce252f88cf94d14976d8010411d037c2873debab116e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NWOU6MHM4KCGCBFEW7PW5762CI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alan Ritter, Ethan Mendes, Hyungjoo Chae, Jay DeYoung, Jungsoo Park, Varsha Kishore, Wei Xu","submitted_at":"2026-05-20T05:43:40Z","abstract_excerpt":"Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates without ensuring calibrated predictive distributions. This limits applications requiring candidate ranking or uncertainty estimation. We introduce Distribution-Aware Reward, an on-policy reinforcement learning objective whose main contribution is to train language models to produce better predictive distributions for regression tasks, rather than only optimizin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20740","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/2605.20740/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":"2026-05-21T01:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N3QmMe8aXpPYvNrnB+N2hsS01Hafyo8Yx6ChcHRwmthjG1sf+bIB2i5mD+z1R8oKvRaJtlBoVSWEBZYPnbMFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:47:23.572296Z"},"content_sha256":"71d57939f55caa769330d0aa0d0623489633ff83e7623de6212960f5cd6f03df","schema_version":"1.0","event_id":"sha256:71d57939f55caa769330d0aa0d0623489633ff83e7623de6212960f5cd6f03df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NWOU6MHM4KCGCBFEW7PW5762CI/bundle.json","state_url":"https://pith.science/pith/NWOU6MHM4KCGCBFEW7PW5762CI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NWOU6MHM4KCGCBFEW7PW5762CI/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":"2026-05-21T12:47:23Z","links":{"resolver":"https://pith.science/pith/NWOU6MHM4KCGCBFEW7PW5762CI","bundle":"https://pith.science/pith/NWOU6MHM4KCGCBFEW7PW5762CI/bundle.json","state":"https://pith.science/pith/NWOU6MHM4KCGCBFEW7PW5762CI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NWOU6MHM4KCGCBFEW7PW5762CI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NWOU6MHM4KCGCBFEW7PW5762CI","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":"ca0aa2e60ef6d78088f20b42d4c67eb0b5839af53ed2cd83cc898654195cda16","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:43:40Z","title_canon_sha256":"ff1bb9af79ccceca54bef0eedfb7c3fe03f639d94b4ca3705c921b0b6584fff7"},"schema_version":"1.0","source":{"id":"2605.20740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20740","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20740v1","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20740","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"NWOU6MHM4KCG","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"NWOU6MHM4KCGCBFE","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"NWOU6MHM","created_at":"2026-05-21T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:71d57939f55caa769330d0aa0d0623489633ff83e7623de6212960f5cd6f03df","target":"graph","created_at":"2026-05-21T01:04:51Z","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/2605.20740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates without ensuring calibrated predictive distributions. This limits applications requiring candidate ranking or uncertainty estimation. We introduce Distribution-Aware Reward, an on-policy reinforcement learning objective whose main contribution is to train language models to produce better predictive distributions for regression tasks, rather than only optimizin","authors_text":"Alan Ritter, Ethan Mendes, Hyungjoo Chae, Jay DeYoung, Jungsoo Park, Varsha Kishore, Wei Xu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:43:40Z","title":"Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20740","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:a762d5678784960ec7dce252f88cf94d14976d8010411d037c2873debab116e6","target":"record","created_at":"2026-05-21T01:04:51Z","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":"ca0aa2e60ef6d78088f20b42d4c67eb0b5839af53ed2cd83cc898654195cda16","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:43:40Z","title_canon_sha256":"ff1bb9af79ccceca54bef0eedfb7c3fe03f639d94b4ca3705c921b0b6584fff7"},"schema_version":"1.0","source":{"id":"2605.20740","kind":"arxiv","version":1}},"canonical_sha256":"6d9d4f30ece2846104a4b7df6effda12209e95fb3c14a7f868d4e338e7a01edc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d9d4f30ece2846104a4b7df6effda12209e95fb3c14a7f868d4e338e7a01edc","first_computed_at":"2026-05-21T01:04:51.671849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:51.671849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yQulVuV+ZLc6JspOj0yTlwbelwrRiVQbRVEgkAKuXfhLKBosxs9/4gD1eAq3xqKTKeXPgd7lUxUxDjfcdjNMDA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:51.672487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a762d5678784960ec7dce252f88cf94d14976d8010411d037c2873debab116e6","sha256:71d57939f55caa769330d0aa0d0623489633ff83e7623de6212960f5cd6f03df"],"state_sha256":"1afe0cca63e18a85c31e23a64f8b1606cabb527d86cb72e5429645a8489713f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mQlhnvG0XsWR5S8zNKzb4nwkFl4xRsoFPuAS+LawjNpnbF/BrIlDrMBSOFEZjppekhYWhnTvq08DCexq1p4yAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T12:47:23.574520Z","bundle_sha256":"a84b7e18e2b2adfe31aede10837b18bd065802fd46fe1d3a20758918ed9c16bf"}}