{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZB2UNG3MIARQ4O7RD66ECQBZUZ","short_pith_number":"pith:ZB2UNG3M","canonical_record":{"source":{"id":"2506.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T18:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"32b6c7ea8d4a31fb2988639041ecf0f6e0ce9c5643ae9d15dcabc7ada44c051e","abstract_canon_sha256":"94ecc17ede39f552101fdab51087d1f57ee26886a7d21c8fd71bad4d0f5a9bf1"},"schema_version":"1.0"},"canonical_sha256":"c875469b6c40230e3bf11fbc414039a64261bf82530a73a85e89a240a76da913","source":{"kind":"arxiv","id":"2506.06887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06887","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06887v1","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06887","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZB2UNG3MIARQ","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZB2UNG3MIARQ4O7R","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZB2UNG3M","created_at":"2026-07-05T11:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZB2UNG3MIARQ4O7RD66ECQBZUZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T18:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"32b6c7ea8d4a31fb2988639041ecf0f6e0ce9c5643ae9d15dcabc7ada44c051e","abstract_canon_sha256":"94ecc17ede39f552101fdab51087d1f57ee26886a7d21c8fd71bad4d0f5a9bf1"},"schema_version":"1.0"},"canonical_sha256":"c875469b6c40230e3bf11fbc414039a64261bf82530a73a85e89a240a76da913","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:57.593327Z","signature_b64":"GYO+MndQGkSbFc8iPD1fl96W8srEntsS6/LEHzcLpFpArJ+b4IGlIACKByb3uWAY2yYZljC6XpGQzwLR0pydAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c875469b6c40230e3bf11fbc414039a64261bf82530a73a85e89a240a76da913","last_reissued_at":"2026-07-05T11:17:57.592862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:57.592862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06887","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":"2026-07-05T11:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXXy+oL3b9WhlB8Xfyi/VLbJve3ZP1lSvBtmzuPJt3cdRPsEhYxXcg7eT48uFCUZU9FKFSp+UQDW62yd6HuCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:54:23.664654Z"},"content_sha256":"33bf8ad627c14b67676f28904f36ee1b490fe73f49571a69615e24cf0128e0cc","schema_version":"1.0","event_id":"sha256:33bf8ad627c14b67676f28904f36ee1b490fe73f49571a69615e24cf0128e0cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZB2UNG3MIARQ4O7RD66ECQBZUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixture of Small and Large Models for Chinese Spelling Check","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Houquan Zhou, Zhenghua Li, Ziheng Qiao","submitted_at":"2025-06-07T18:29:10Z","abstract_excerpt":"In the era of large language models (LLMs), the Chinese Spelling Check (CSC) task has seen various LLM methods developed, yet their performance remains unsatisfactory. In contrast, fine-tuned BERT-based models, relying on high-quality in-domain data, show excellent performance but suffer from edit pattern overfitting. This paper proposes a novel dynamic mixture approach that effectively combines the probability distributions of small models and LLMs during the beam search decoding phase, achieving a balanced enhancement of precise corrections from small models and the fluency of LLMs. This app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06887","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/2506.06887/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":"2026-07-05T11:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIf6DaC0Lv3QoN8NMnVZ+2Zp+n0ylHd712OVuMtvoKweITLuS7U9WLoNnG79KbKLl3JEQY/i52tKn5iEANU2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:54:23.665181Z"},"content_sha256":"260f6539b274aae09ec2557faef856e59991feb6dd5f110a9624eb378f23db14","schema_version":"1.0","event_id":"sha256:260f6539b274aae09ec2557faef856e59991feb6dd5f110a9624eb378f23db14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ/bundle.json","state_url":"https://pith.science/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ/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":"2026-08-09T22:54:23Z","links":{"resolver":"https://pith.science/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ","bundle":"https://pith.science/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ/bundle.json","state":"https://pith.science/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZB2UNG3MIARQ4O7RD66ECQBZUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZB2UNG3MIARQ4O7RD66ECQBZUZ","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":"94ecc17ede39f552101fdab51087d1f57ee26886a7d21c8fd71bad4d0f5a9bf1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T18:29:10Z","title_canon_sha256":"32b6c7ea8d4a31fb2988639041ecf0f6e0ce9c5643ae9d15dcabc7ada44c051e"},"schema_version":"1.0","source":{"id":"2506.06887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06887","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06887v1","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06887","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZB2UNG3MIARQ","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZB2UNG3MIARQ4O7R","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZB2UNG3M","created_at":"2026-07-05T11:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:260f6539b274aae09ec2557faef856e59991feb6dd5f110a9624eb378f23db14","target":"graph","created_at":"2026-07-05T11:17:57Z","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/2506.06887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of large language models (LLMs), the Chinese Spelling Check (CSC) task has seen various LLM methods developed, yet their performance remains unsatisfactory. In contrast, fine-tuned BERT-based models, relying on high-quality in-domain data, show excellent performance but suffer from edit pattern overfitting. This paper proposes a novel dynamic mixture approach that effectively combines the probability distributions of small models and LLMs during the beam search decoding phase, achieving a balanced enhancement of precise corrections from small models and the fluency of LLMs. This app","authors_text":"Houquan Zhou, Zhenghua Li, Ziheng Qiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T18:29:10Z","title":"Mixture of Small and Large Models for Chinese Spelling Check"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06887","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":"sha256:33bf8ad627c14b67676f28904f36ee1b490fe73f49571a69615e24cf0128e0cc","target":"record","created_at":"2026-07-05T11:17:57Z","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":"94ecc17ede39f552101fdab51087d1f57ee26886a7d21c8fd71bad4d0f5a9bf1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T18:29:10Z","title_canon_sha256":"32b6c7ea8d4a31fb2988639041ecf0f6e0ce9c5643ae9d15dcabc7ada44c051e"},"schema_version":"1.0","source":{"id":"2506.06887","kind":"arxiv","version":1}},"canonical_sha256":"c875469b6c40230e3bf11fbc414039a64261bf82530a73a85e89a240a76da913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c875469b6c40230e3bf11fbc414039a64261bf82530a73a85e89a240a76da913","first_computed_at":"2026-07-05T11:17:57.592862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:57.592862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GYO+MndQGkSbFc8iPD1fl96W8srEntsS6/LEHzcLpFpArJ+b4IGlIACKByb3uWAY2yYZljC6XpGQzwLR0pydAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:57.593327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33bf8ad627c14b67676f28904f36ee1b490fe73f49571a69615e24cf0128e0cc","sha256:260f6539b274aae09ec2557faef856e59991feb6dd5f110a9624eb378f23db14"],"state_sha256":"4cb410a1272609bed793a43cbad2da2344fb713aa0882ac14694222ddb466b01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aeySfDQnKjZau2ne60EqBFVHTGQsn9k9DzMDvg22mns16pnngLFqdKsYnyC3TvhiYBElxptfZhvsXJeM/DShDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:54:23.670977Z","bundle_sha256":"14c35c9588f351915a59bab5334a1c05386e3970617da7d04a86bc5a244f86ab"}}