{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HZAUJL73RNSIRUIRD2XCVSIQJU","short_pith_number":"pith:HZAUJL73","canonical_record":{"source":{"id":"2605.17458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T14:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"b95818488fbde6d01d7c8fd7f330fa48ab3a14bb716ed371ebfeaf9c9575227d","abstract_canon_sha256":"5b1898a3c25c8dbe564a00938976d203c95474a9141e5e05aac00c3c402dc72b"},"schema_version":"1.0"},"canonical_sha256":"3e4144affb8b6488d1111eae2ac9104d3dad874b12903e72779e0d5434ce1e98","source":{"kind":"arxiv","id":"2605.17458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17458","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17458v1","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17458","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"HZAUJL73RNSI","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"HZAUJL73RNSIRUIR","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"HZAUJL73","created_at":"2026-05-20T00:04:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HZAUJL73RNSIRUIRD2XCVSIQJU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T14:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"b95818488fbde6d01d7c8fd7f330fa48ab3a14bb716ed371ebfeaf9c9575227d","abstract_canon_sha256":"5b1898a3c25c8dbe564a00938976d203c95474a9141e5e05aac00c3c402dc72b"},"schema_version":"1.0"},"canonical_sha256":"3e4144affb8b6488d1111eae2ac9104d3dad874b12903e72779e0d5434ce1e98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:40.035747Z","signature_b64":"SsFwnB9IN4MSuVPWJfZ2fTnDnPavayJ+GGxp102rLLGGw4+fbEH37KwPftkcQMB4t36zgSTLMdC11VXPMDtKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4144affb8b6488d1111eae2ac9104d3dad874b12903e72779e0d5434ce1e98","last_reissued_at":"2026-05-20T00:04:40.034727Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:40.034727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17458","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":"2026-05-20T00:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOvC/Wm11+D4faZPSmFUZMPu9gpjVy8rvTsStvC/8C4xu8fAmGVDLn/Z+FBcZ4eminVUj1widHAMV+KkOFlXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:45:18.200455Z"},"content_sha256":"7076c75a33a854e36721214218a64428056cf0e4d4b434bc0bec57a167255db6","schema_version":"1.0","event_id":"sha256:7076c75a33a854e36721214218a64428056cf0e4d4b434bc0bec57a167255db6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HZAUJL73RNSIRUIRD2XCVSIQJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiayin Wang, Tianxiang Xu, Xiaoyan Zhu, Xin Lai","submitted_at":"2026-05-17T14:00:01Z","abstract_excerpt":"Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among samples, which limits the model's ability to shape decision boundaries and calibrate predictive confidence. In this paper, we propose ClaHF, a human feedback-inspired reinforcement learning (RL) framework for text classification that integrates preference modeling and RL optimization into the classification pipeline without requiring additional human annotations. U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17458","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/2605.17458/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.707743Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.662034Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"256f6f7579bf297ab181e375dd156a29f66ba6f3ffe9aac4cd44be493b9f6490"},"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":"2026-05-20T00:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b+8ITy1AWKisGPw8gKOxGIjuALZVClzuhApm3Lh+j4oUBQCXXi3/GZZniHtT9HoFC6tdhL0/SXy5AYI/dUHhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:45:18.200891Z"},"content_sha256":"12685c7d689c2204f6b47ed969057dfb08f919e6505ffdad27ede60eb88c8ae2","schema_version":"1.0","event_id":"sha256:12685c7d689c2204f6b47ed969057dfb08f919e6505ffdad27ede60eb88c8ae2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZAUJL73RNSIRUIRD2XCVSIQJU/bundle.json","state_url":"https://pith.science/pith/HZAUJL73RNSIRUIRD2XCVSIQJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZAUJL73RNSIRUIRD2XCVSIQJU/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":"2026-05-26T01:45:18Z","links":{"resolver":"https://pith.science/pith/HZAUJL73RNSIRUIRD2XCVSIQJU","bundle":"https://pith.science/pith/HZAUJL73RNSIRUIRD2XCVSIQJU/bundle.json","state":"https://pith.science/pith/HZAUJL73RNSIRUIRD2XCVSIQJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZAUJL73RNSIRUIRD2XCVSIQJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HZAUJL73RNSIRUIRD2XCVSIQJU","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":"5b1898a3c25c8dbe564a00938976d203c95474a9141e5e05aac00c3c402dc72b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T14:00:01Z","title_canon_sha256":"b95818488fbde6d01d7c8fd7f330fa48ab3a14bb716ed371ebfeaf9c9575227d"},"schema_version":"1.0","source":{"id":"2605.17458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17458","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17458v1","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17458","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"HZAUJL73RNSI","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"HZAUJL73RNSIRUIR","created_at":"2026-05-20T00:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"HZAUJL73","created_at":"2026-05-20T00:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:12685c7d689c2204f6b47ed969057dfb08f919e6505ffdad27ede60eb88c8ae2","target":"graph","created_at":"2026-05-20T00:04:40Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.707743Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.662034Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17458/integrity.json","findings":[],"snapshot_sha256":"256f6f7579bf297ab181e375dd156a29f66ba6f3ffe9aac4cd44be493b9f6490","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among samples, which limits the model's ability to shape decision boundaries and calibrate predictive confidence. In this paper, we propose ClaHF, a human feedback-inspired reinforcement learning (RL) framework for text classification that integrates preference modeling and RL optimization into the classification pipeline without requiring additional human annotations. U","authors_text":"Jiayin Wang, Tianxiang Xu, Xiaoyan Zhu, Xin Lai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T14:00:01Z","title":"ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17458","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":"sha256:7076c75a33a854e36721214218a64428056cf0e4d4b434bc0bec57a167255db6","target":"record","created_at":"2026-05-20T00:04:40Z","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":"5b1898a3c25c8dbe564a00938976d203c95474a9141e5e05aac00c3c402dc72b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T14:00:01Z","title_canon_sha256":"b95818488fbde6d01d7c8fd7f330fa48ab3a14bb716ed371ebfeaf9c9575227d"},"schema_version":"1.0","source":{"id":"2605.17458","kind":"arxiv","version":1}},"canonical_sha256":"3e4144affb8b6488d1111eae2ac9104d3dad874b12903e72779e0d5434ce1e98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e4144affb8b6488d1111eae2ac9104d3dad874b12903e72779e0d5434ce1e98","first_computed_at":"2026-05-20T00:04:40.034727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:40.034727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SsFwnB9IN4MSuVPWJfZ2fTnDnPavayJ+GGxp102rLLGGw4+fbEH37KwPftkcQMB4t36zgSTLMdC11VXPMDtKBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:40.035747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7076c75a33a854e36721214218a64428056cf0e4d4b434bc0bec57a167255db6","sha256:12685c7d689c2204f6b47ed969057dfb08f919e6505ffdad27ede60eb88c8ae2"],"state_sha256":"a391e51737c440f272b89a08aa9b807072c0b45d57ad927ea1d9c8c15ab0a53c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mp71cs6sxgXC2HNagedeJbNkj/6u+FisayYfjl5/GX8jKE3XGu4zSuAYJFCmnbZRpGoUgYvH6ZFNEe2IWKRzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:45:18.203626Z","bundle_sha256":"49c1186a1e9cd8e5826ad067de0be7a181c219ba66f0a6d3a398ea49449b3cf7"}}