{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TXN65WMTBKD7CBIEVL6GHOXCU7","short_pith_number":"pith:TXN65WMT","canonical_record":{"source":{"id":"2606.00020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T02:06:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2955f5668cf29380a9ce3555aee0ae3d730f5ae80f76ad190343a09305e0f293","abstract_canon_sha256":"ff3101135cd528e946037c440da3f339cb51f9020f79f2e4aaf4a71a11c20285"},"schema_version":"1.0"},"canonical_sha256":"9ddbeed9930a87f10504aafc63bae2a7ed66f0cce57658020def5fa528dd25f6","source":{"kind":"arxiv","id":"2606.00020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00020","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00020v1","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00020","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"pith_short_12","alias_value":"TXN65WMTBKD7","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"pith_short_16","alias_value":"TXN65WMTBKD7CBIE","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"pith_short_8","alias_value":"TXN65WMT","created_at":"2026-06-02T00:03:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TXN65WMTBKD7CBIEVL6GHOXCU7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T02:06:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2955f5668cf29380a9ce3555aee0ae3d730f5ae80f76ad190343a09305e0f293","abstract_canon_sha256":"ff3101135cd528e946037c440da3f339cb51f9020f79f2e4aaf4a71a11c20285"},"schema_version":"1.0"},"canonical_sha256":"9ddbeed9930a87f10504aafc63bae2a7ed66f0cce57658020def5fa528dd25f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:12.546498Z","signature_b64":"6PHXwcOKTVWw+wSwuwKe0Q/HmcbIbe/l3+GpsTcFXwJtPrjhUMr/w4/0iUreSfzGMbD+7UIEqdljzXYtvrsTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ddbeed9930a87f10504aafc63bae2a7ed66f0cce57658020def5fa528dd25f6","last_reissued_at":"2026-06-02T00:03:12.546026Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:12.546026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00020","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":"2026-06-02T00:03:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKMNSLzxYnKxQGNyd5sQ9uLGe010zlCqLlqa9rT/0odwn1obSwe7XJ9BMa2rIH3oAObuG8tzRT9pWqH/N0UVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:29:27.811247Z"},"content_sha256":"080bb1ab3249d055902bd15396c11a4f8265510281248d5c4c6eb8c8e40a07e2","schema_version":"1.0","event_id":"sha256:080bb1ab3249d055902bd15396c11a4f8265510281248d5c4c6eb8c8e40a07e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TXN65WMTBKD7CBIEVL6GHOXCU7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Man Lan, Wei Tian, Yuhao Zhou","submitted_at":"2026-04-14T02:06:38Z","abstract_excerpt":"Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics, leading to systematic over-correction. We propose CSRP, a three-stage framework that progressively builds correction capability through Continual Pre-training (CPT) on 5.9M balanced samples to internalize domain knowledge, Chain-of-Thought SFT with explicit error reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00020","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/2606.00020/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":"2026-06-02T00:03:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xEOnn4MROVeGhrxH4w1Czvm8kY4JZhREcU34e3F2P13P2zf84j3AcGKody8vC+sxzP7K3ltcFrWdAZkMqv8eDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:29:27.811645Z"},"content_sha256":"95909110d1bcd545047bf9fdcbb8ba9dcd4c1fcb9ef063191b26f813d0f88a11","schema_version":"1.0","event_id":"sha256:95909110d1bcd545047bf9fdcbb8ba9dcd4c1fcb9ef063191b26f813d0f88a11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXN65WMTBKD7CBIEVL6GHOXCU7/bundle.json","state_url":"https://pith.science/pith/TXN65WMTBKD7CBIEVL6GHOXCU7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXN65WMTBKD7CBIEVL6GHOXCU7/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":"2026-06-04T00:29:27Z","links":{"resolver":"https://pith.science/pith/TXN65WMTBKD7CBIEVL6GHOXCU7","bundle":"https://pith.science/pith/TXN65WMTBKD7CBIEVL6GHOXCU7/bundle.json","state":"https://pith.science/pith/TXN65WMTBKD7CBIEVL6GHOXCU7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXN65WMTBKD7CBIEVL6GHOXCU7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXN65WMTBKD7CBIEVL6GHOXCU7","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":"ff3101135cd528e946037c440da3f339cb51f9020f79f2e4aaf4a71a11c20285","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T02:06:38Z","title_canon_sha256":"2955f5668cf29380a9ce3555aee0ae3d730f5ae80f76ad190343a09305e0f293"},"schema_version":"1.0","source":{"id":"2606.00020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00020","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00020v1","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00020","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"pith_short_12","alias_value":"TXN65WMTBKD7","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"pith_short_16","alias_value":"TXN65WMTBKD7CBIE","created_at":"2026-06-02T00:03:12Z"},{"alias_kind":"pith_short_8","alias_value":"TXN65WMT","created_at":"2026-06-02T00:03:12Z"}],"graph_snapshots":[{"event_id":"sha256:95909110d1bcd545047bf9fdcbb8ba9dcd4c1fcb9ef063191b26f813d0f88a11","target":"graph","created_at":"2026-06-02T00:03:12Z","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/2606.00020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics, leading to systematic over-correction. We propose CSRP, a three-stage framework that progressively builds correction capability through Continual Pre-training (CPT) on 5.9M balanced samples to internalize domain knowledge, Chain-of-Thought SFT with explicit error reasoning","authors_text":"Man Lan, Wei Tian, Yuhao Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T02:06:38Z","title":"CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00020","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":"sha256:080bb1ab3249d055902bd15396c11a4f8265510281248d5c4c6eb8c8e40a07e2","target":"record","created_at":"2026-06-02T00:03:12Z","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":"ff3101135cd528e946037c440da3f339cb51f9020f79f2e4aaf4a71a11c20285","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T02:06:38Z","title_canon_sha256":"2955f5668cf29380a9ce3555aee0ae3d730f5ae80f76ad190343a09305e0f293"},"schema_version":"1.0","source":{"id":"2606.00020","kind":"arxiv","version":1}},"canonical_sha256":"9ddbeed9930a87f10504aafc63bae2a7ed66f0cce57658020def5fa528dd25f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ddbeed9930a87f10504aafc63bae2a7ed66f0cce57658020def5fa528dd25f6","first_computed_at":"2026-06-02T00:03:12.546026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T00:03:12.546026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6PHXwcOKTVWw+wSwuwKe0Q/HmcbIbe/l3+GpsTcFXwJtPrjhUMr/w4/0iUreSfzGMbD+7UIEqdljzXYtvrsTCQ==","signature_status":"signed_v1","signed_at":"2026-06-02T00:03:12.546498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:080bb1ab3249d055902bd15396c11a4f8265510281248d5c4c6eb8c8e40a07e2","sha256:95909110d1bcd545047bf9fdcbb8ba9dcd4c1fcb9ef063191b26f813d0f88a11"],"state_sha256":"1f066167f23540b7aa27139305c55f0451f76cce41164c649a9f595976c5fccd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkUcihciVGiay2KvcqQa6mI8Gtba65z/yUItrEV6VDtePiPkLMlqQ7hufp45fIeSVjSuWeBdlgVMDW+u+140CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T00:29:27.813768Z","bundle_sha256":"c571d28684f5d7c6d46299e26e690b1b23dcb0403e305ba6f64be425b466925b"}}