{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SZHZPKIBEVW2RT4UC27TL27F5V","short_pith_number":"pith:SZHZPKIB","canonical_record":{"source":{"id":"2403.11558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T08:18:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"220f6248e5419ca59d57d10f2701b8d877f1a9798a9af2f6c681517667fb71b6","abstract_canon_sha256":"b5dedc1f1f37071c5f2a7300da2bfbfc13a41202d2a923219e037d8870565309"},"schema_version":"1.0"},"canonical_sha256":"964f97a901256da8cf9416bf35ebe5ed5cb516b67517a8ebc6d604ea00525975","source":{"kind":"arxiv","id":"2403.11558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11558","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11558v1","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11558","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"pith_short_12","alias_value":"SZHZPKIBEVW2","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"pith_short_16","alias_value":"SZHZPKIBEVW2RT4U","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"pith_short_8","alias_value":"SZHZPKIB","created_at":"2026-07-05T07:57:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SZHZPKIBEVW2RT4UC27TL27F5V","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T08:18:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"220f6248e5419ca59d57d10f2701b8d877f1a9798a9af2f6c681517667fb71b6","abstract_canon_sha256":"b5dedc1f1f37071c5f2a7300da2bfbfc13a41202d2a923219e037d8870565309"},"schema_version":"1.0"},"canonical_sha256":"964f97a901256da8cf9416bf35ebe5ed5cb516b67517a8ebc6d604ea00525975","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:18.325567Z","signature_b64":"viKZmYCVTZ17HBXTbUgNKKq8oPpy17K6WS++v9SjtA/lQTNsCYQXRIDhHVXE9T5DUE1yQHwkD7U83DVrSdBeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"964f97a901256da8cf9416bf35ebe5ed5cb516b67517a8ebc6d604ea00525975","last_reissued_at":"2026-07-05T07:57:18.325013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:18.325013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11558","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":"2026-07-05T07:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSr5vGMoFToa6mibbe53e4LrTtPJ8C816Uu0PfcH3L8GGwXrjk2daoh7gKl/3ihHr5cPBmdWq/3fFDKhbqTSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:06:14.587268Z"},"content_sha256":"f4baa8f7055948ef8cb59734220b6772d091c533070fb7551e471ed8374890d5","schema_version":"1.0","event_id":"sha256:f4baa8f7055948ef8cb59734220b6772d091c533070fb7551e471ed8374890d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SZHZPKIBEVW2RT4UC27TL27F5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dangyang Chen, Kaihe Xu, Wei Wei, Wendi Li, Wenfeng Xie, Yu Cheng","submitted_at":"2024-03-18T08:18:37Z","abstract_excerpt":"To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11558","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/2403.11558/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":"2026-07-05T07:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tiJm1+YGI05zfDUocPXPSDvLmsPkZMk72Mxekfx96dQcNgATquMIVEphT7gM9OqijWKpRjUHY7bvcKuMKj6XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:06:14.587796Z"},"content_sha256":"b1c7d46da61acb1bcf5ced780016918ae5fdfb8d8d8bcba9b6bb0f2713282b7d","schema_version":"1.0","event_id":"sha256:b1c7d46da61acb1bcf5ced780016918ae5fdfb8d8d8bcba9b6bb0f2713282b7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZHZPKIBEVW2RT4UC27TL27F5V/bundle.json","state_url":"https://pith.science/pith/SZHZPKIBEVW2RT4UC27TL27F5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZHZPKIBEVW2RT4UC27TL27F5V/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":"2026-08-11T01:06:14Z","links":{"resolver":"https://pith.science/pith/SZHZPKIBEVW2RT4UC27TL27F5V","bundle":"https://pith.science/pith/SZHZPKIBEVW2RT4UC27TL27F5V/bundle.json","state":"https://pith.science/pith/SZHZPKIBEVW2RT4UC27TL27F5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZHZPKIBEVW2RT4UC27TL27F5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SZHZPKIBEVW2RT4UC27TL27F5V","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":"b5dedc1f1f37071c5f2a7300da2bfbfc13a41202d2a923219e037d8870565309","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T08:18:37Z","title_canon_sha256":"220f6248e5419ca59d57d10f2701b8d877f1a9798a9af2f6c681517667fb71b6"},"schema_version":"1.0","source":{"id":"2403.11558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11558","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11558v1","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11558","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"pith_short_12","alias_value":"SZHZPKIBEVW2","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"pith_short_16","alias_value":"SZHZPKIBEVW2RT4U","created_at":"2026-07-05T07:57:18Z"},{"alias_kind":"pith_short_8","alias_value":"SZHZPKIB","created_at":"2026-07-05T07:57:18Z"}],"graph_snapshots":[{"event_id":"sha256:b1c7d46da61acb1bcf5ced780016918ae5fdfb8d8d8bcba9b6bb0f2713282b7d","target":"graph","created_at":"2026-07-05T07:57:18Z","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/2403.11558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel re","authors_text":"Dangyang Chen, Kaihe Xu, Wei Wei, Wendi Li, Wenfeng Xie, Yu Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T08:18:37Z","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11558","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:f4baa8f7055948ef8cb59734220b6772d091c533070fb7551e471ed8374890d5","target":"record","created_at":"2026-07-05T07:57:18Z","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":"b5dedc1f1f37071c5f2a7300da2bfbfc13a41202d2a923219e037d8870565309","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T08:18:37Z","title_canon_sha256":"220f6248e5419ca59d57d10f2701b8d877f1a9798a9af2f6c681517667fb71b6"},"schema_version":"1.0","source":{"id":"2403.11558","kind":"arxiv","version":1}},"canonical_sha256":"964f97a901256da8cf9416bf35ebe5ed5cb516b67517a8ebc6d604ea00525975","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"964f97a901256da8cf9416bf35ebe5ed5cb516b67517a8ebc6d604ea00525975","first_computed_at":"2026-07-05T07:57:18.325013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:18.325013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"viKZmYCVTZ17HBXTbUgNKKq8oPpy17K6WS++v9SjtA/lQTNsCYQXRIDhHVXE9T5DUE1yQHwkD7U83DVrSdBeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:18.325567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4baa8f7055948ef8cb59734220b6772d091c533070fb7551e471ed8374890d5","sha256:b1c7d46da61acb1bcf5ced780016918ae5fdfb8d8d8bcba9b6bb0f2713282b7d"],"state_sha256":"b14ec4a8c3f98dd3d6ee2dace2f6a88f110e243d757ff00eb7aafc91b7037d62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJ1AvxrWDVsgOgMckJtsS6nW/U81qwBw0cWwCZ/DIYF0LFgrp42VwAacypa12/FD0gRxLRmzeMQGQepMJ/FvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:06:14.600731Z","bundle_sha256":"1eb2e21e7dca727b402b1c760b7f619a17bd9ffe65f4e2ae1e36ca62e3aa5b55"}}