{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CV6UPV3VSE6I7GQOQGZODCD6C2","short_pith_number":"pith:CV6UPV3V","canonical_record":{"source":{"id":"2310.19651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T15:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"934df2f567610e9f8a1f968b15004c5177191729024c4029d3944cda9a289b1a","abstract_canon_sha256":"4169d5fc8f5961ad11bd57e8e0ddc819d40c543f2e00c8301871d848938f0428"},"schema_version":"1.0"},"canonical_sha256":"157d47d775913c8f9a0e81b2e1887e16af2bc885b3064ac07ff957b9606944c3","source":{"kind":"arxiv","id":"2310.19651","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19651","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19651v3","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19651","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"CV6UPV3VSE6I","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"CV6UPV3VSE6I7GQO","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"CV6UPV3V","created_at":"2026-07-05T10:22:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CV6UPV3VSE6I7GQOQGZODCD6C2","target":"record","payload":{"canonical_record":{"source":{"id":"2310.19651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T15:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"934df2f567610e9f8a1f968b15004c5177191729024c4029d3944cda9a289b1a","abstract_canon_sha256":"4169d5fc8f5961ad11bd57e8e0ddc819d40c543f2e00c8301871d848938f0428"},"schema_version":"1.0"},"canonical_sha256":"157d47d775913c8f9a0e81b2e1887e16af2bc885b3064ac07ff957b9606944c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:43.360257Z","signature_b64":"6L1LXGDub4Fw6OXPlerHDhYipmU5BpcyR8XtYyzdKEyg4aVp4pFanfemHCP7mGaR3ZdW7IByg7Ji7MueZS5fDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"157d47d775913c8f9a0e81b2e1887e16af2bc885b3064ac07ff957b9606944c3","last_reissued_at":"2026-07-05T10:22:43.359765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:43.359765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.19651","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYW+GokFkFl1oyslNSXrI9pHtz3VxfaUIKrcPTCAeG18Fe0vtoWEaPCfFZ8fPyEKdYTTjk5jXzhFMmH2NJZ0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:04:09.402127Z"},"content_sha256":"a008d80eb0da6d6fa457d3738ee94fd33080230bb1c022a673936ad61bf23d62","schema_version":"1.0","event_id":"sha256:a008d80eb0da6d6fa457d3738ee94fd33080230bb1c022a673936ad61bf23d62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CV6UPV3VSE6I7GQOQGZODCD6C2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamics of Instruction Fine-Tuning for Chinese Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chiyu Song, Jianhao Yan, Yuejiao Fei, Yue Zhang, Zhanchao Zhou, Zhenzhong Lan","submitted_at":"2023-10-30T15:37:10Z","abstract_excerpt":"Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models (LLMs). While numerous studies have examined the impact of factors such as data volume and model size on English models, the scaling properties of instruction tuning in other languages remain largely unexplored. In this work, we systematically investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese LLMs. We utilize a newly curated dataset, DoIT, which includes over 40,000 high-quality instruction instances covering ten underlying ab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19651","kind":"arxiv","version":3},"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/2310.19651/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":"2026-07-05T10:22:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPXGazRjyK9ARl/WYp94ig1gcxvL7sDpCL9QKfCL0H786QORN071brIv5CQbecsc9Blcwr1TPSVMGJgrdPNmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:04:09.402977Z"},"content_sha256":"cfaf22c7745ba73c568e23e9edc867cb9608797fb64a51366e5199d990ced307","schema_version":"1.0","event_id":"sha256:cfaf22c7745ba73c568e23e9edc867cb9608797fb64a51366e5199d990ced307"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CV6UPV3VSE6I7GQOQGZODCD6C2/bundle.json","state_url":"https://pith.science/pith/CV6UPV3VSE6I7GQOQGZODCD6C2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CV6UPV3VSE6I7GQOQGZODCD6C2/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":"2026-08-07T05:04:09Z","links":{"resolver":"https://pith.science/pith/CV6UPV3VSE6I7GQOQGZODCD6C2","bundle":"https://pith.science/pith/CV6UPV3VSE6I7GQOQGZODCD6C2/bundle.json","state":"https://pith.science/pith/CV6UPV3VSE6I7GQOQGZODCD6C2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CV6UPV3VSE6I7GQOQGZODCD6C2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CV6UPV3VSE6I7GQOQGZODCD6C2","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":"4169d5fc8f5961ad11bd57e8e0ddc819d40c543f2e00c8301871d848938f0428","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T15:37:10Z","title_canon_sha256":"934df2f567610e9f8a1f968b15004c5177191729024c4029d3944cda9a289b1a"},"schema_version":"1.0","source":{"id":"2310.19651","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19651","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19651v3","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19651","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"CV6UPV3VSE6I","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"CV6UPV3VSE6I7GQO","created_at":"2026-07-05T10:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"CV6UPV3V","created_at":"2026-07-05T10:22:43Z"}],"graph_snapshots":[{"event_id":"sha256:cfaf22c7745ba73c568e23e9edc867cb9608797fb64a51366e5199d990ced307","target":"graph","created_at":"2026-07-05T10:22:43Z","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/2310.19651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models (LLMs). While numerous studies have examined the impact of factors such as data volume and model size on English models, the scaling properties of instruction tuning in other languages remain largely unexplored. In this work, we systematically investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese LLMs. We utilize a newly curated dataset, DoIT, which includes over 40,000 high-quality instruction instances covering ten underlying ab","authors_text":"Chiyu Song, Jianhao Yan, Yuejiao Fei, Yue Zhang, Zhanchao Zhou, Zhenzhong Lan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T15:37:10Z","title":"Dynamics of Instruction Fine-Tuning for Chinese Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19651","kind":"arxiv","version":3},"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:a008d80eb0da6d6fa457d3738ee94fd33080230bb1c022a673936ad61bf23d62","target":"record","created_at":"2026-07-05T10:22:43Z","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":"4169d5fc8f5961ad11bd57e8e0ddc819d40c543f2e00c8301871d848938f0428","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T15:37:10Z","title_canon_sha256":"934df2f567610e9f8a1f968b15004c5177191729024c4029d3944cda9a289b1a"},"schema_version":"1.0","source":{"id":"2310.19651","kind":"arxiv","version":3}},"canonical_sha256":"157d47d775913c8f9a0e81b2e1887e16af2bc885b3064ac07ff957b9606944c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"157d47d775913c8f9a0e81b2e1887e16af2bc885b3064ac07ff957b9606944c3","first_computed_at":"2026-07-05T10:22:43.359765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:43.359765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6L1LXGDub4Fw6OXPlerHDhYipmU5BpcyR8XtYyzdKEyg4aVp4pFanfemHCP7mGaR3ZdW7IByg7Ji7MueZS5fDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:43.360257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19651","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a008d80eb0da6d6fa457d3738ee94fd33080230bb1c022a673936ad61bf23d62","sha256:cfaf22c7745ba73c568e23e9edc867cb9608797fb64a51366e5199d990ced307"],"state_sha256":"4e7cd9466de15f2093a6763434dfdc64ec5b2223e488a4d77ed70c3d5e074db4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o7WI+nxajSAHXAWGaa8XXX5QCYbkC4XscBM/NoIoiO7QRlKaoYRqYy3WyuUvZf9PMI4TsHXJgtwRr0ThKS2UDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:04:09.409190Z","bundle_sha256":"47ea40c954d546a09af57f7ede36f49370fa68fb2106d0b0444ffcfaa6cd88df"}}