{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WAPOKYJ7M5BDDIOJXKWUFN5MWH","short_pith_number":"pith:WAPOKYJ7","canonical_record":{"source":{"id":"2304.07854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-16T18:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"79ba7ac03490cc6b012e8afbdbeb91effea26c8f74dc7aa035709ee6d4f63264","abstract_canon_sha256":"5a0f90ad36d0bceb5f7235218b75c636e1f741a7f1b8e2ed041bdf0faca7254c"},"schema_version":"1.0"},"canonical_sha256":"b01ee5613f674231a1c9baad42b7acb1d0ddaa540a0108fb7e3a8aaa0868f22f","source":{"kind":"arxiv","id":"2304.07854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07854","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07854v1","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07854","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"pith_short_12","alias_value":"WAPOKYJ7M5BD","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"pith_short_16","alias_value":"WAPOKYJ7M5BDDIOJ","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"pith_short_8","alias_value":"WAPOKYJ7","created_at":"2026-07-05T06:01:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WAPOKYJ7M5BDDIOJXKWUFN5MWH","target":"record","payload":{"canonical_record":{"source":{"id":"2304.07854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-16T18:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"79ba7ac03490cc6b012e8afbdbeb91effea26c8f74dc7aa035709ee6d4f63264","abstract_canon_sha256":"5a0f90ad36d0bceb5f7235218b75c636e1f741a7f1b8e2ed041bdf0faca7254c"},"schema_version":"1.0"},"canonical_sha256":"b01ee5613f674231a1c9baad42b7acb1d0ddaa540a0108fb7e3a8aaa0868f22f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:26.101638Z","signature_b64":"UKkbEmyuhO5K+QSVmie0R8s/SwS7KcAojfCk+KaC74dp1vc+Fta1U/E3L7Lu2uZGnE5A6laUw12DNpT9nHkECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b01ee5613f674231a1c9baad42b7acb1d0ddaa540a0108fb7e3a8aaa0868f22f","last_reissued_at":"2026-07-05T06:01:26.101180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:26.101180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.07854","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":"2026-07-05T06:01:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iz0DX4awfPhfzjkLpIAHhTbExmygdoJA/1H3HahCNWq4HuDnknrtquUFXejvQKR+DBUkT2AS88kjtwN9QKgcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:02:49.086577Z"},"content_sha256":"5f79b1721e5d362a3c4f7606e7c31a4c48cfc79db7e05346f916ad19356cde46","schema_version":"1.0","event_id":"sha256:5f79b1721e5d362a3c4f7606e7c31a4c48cfc79db7e05346f916ad19356cde46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WAPOKYJ7M5BDDIOJXKWUFN5MWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baochang Ma, Qiang Niu, Xiangang Li, Yan Gong, Yiping Peng, Yong Deng, Yunjie Ji","submitted_at":"2023-04-16T18:37:39Z","abstract_excerpt":"Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of comprehensive and in-depth evaluations of these models' performance. In this study, we examine the influence of training data factors, including quantity, quality, and linguistic distribution, on model performance. Our analysis is grounded in several publicly accessible, high-quality instruction datasets, as well as our own Chinese multi-turn conversations. We assess "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07854","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/2304.07854/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":"2026-07-05T06:01:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXTUBrz1j3EBP64KAg4BF6XUERkUSzbZrG34yCND2rYB/Pcppq8EMXwIPQtPZ2eK8J4/SaPXk8KHbIY2SO0qDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:02:49.086938Z"},"content_sha256":"d44e4ce02f19508df0681af0af408b56cd4001d119679875485369b4f313b770","schema_version":"1.0","event_id":"sha256:d44e4ce02f19508df0681af0af408b56cd4001d119679875485369b4f313b770"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH/bundle.json","state_url":"https://pith.science/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH/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":"2026-07-07T10:02:49Z","links":{"resolver":"https://pith.science/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH","bundle":"https://pith.science/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH/bundle.json","state":"https://pith.science/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAPOKYJ7M5BDDIOJXKWUFN5MWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WAPOKYJ7M5BDDIOJXKWUFN5MWH","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":"5a0f90ad36d0bceb5f7235218b75c636e1f741a7f1b8e2ed041bdf0faca7254c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-16T18:37:39Z","title_canon_sha256":"79ba7ac03490cc6b012e8afbdbeb91effea26c8f74dc7aa035709ee6d4f63264"},"schema_version":"1.0","source":{"id":"2304.07854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07854","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07854v1","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07854","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"pith_short_12","alias_value":"WAPOKYJ7M5BD","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"pith_short_16","alias_value":"WAPOKYJ7M5BDDIOJ","created_at":"2026-07-05T06:01:26Z"},{"alias_kind":"pith_short_8","alias_value":"WAPOKYJ7","created_at":"2026-07-05T06:01:26Z"}],"graph_snapshots":[{"event_id":"sha256:d44e4ce02f19508df0681af0af408b56cd4001d119679875485369b4f313b770","target":"graph","created_at":"2026-07-05T06:01:26Z","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/2304.07854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of comprehensive and in-depth evaluations of these models' performance. In this study, we examine the influence of training data factors, including quantity, quality, and linguistic distribution, on model performance. Our analysis is grounded in several publicly accessible, high-quality instruction datasets, as well as our own Chinese multi-turn conversations. We assess ","authors_text":"Baochang Ma, Qiang Niu, Xiangang Li, Yan Gong, Yiping Peng, Yong Deng, Yunjie Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-16T18:37:39Z","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07854","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":"sha256:5f79b1721e5d362a3c4f7606e7c31a4c48cfc79db7e05346f916ad19356cde46","target":"record","created_at":"2026-07-05T06:01:26Z","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":"5a0f90ad36d0bceb5f7235218b75c636e1f741a7f1b8e2ed041bdf0faca7254c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-16T18:37:39Z","title_canon_sha256":"79ba7ac03490cc6b012e8afbdbeb91effea26c8f74dc7aa035709ee6d4f63264"},"schema_version":"1.0","source":{"id":"2304.07854","kind":"arxiv","version":1}},"canonical_sha256":"b01ee5613f674231a1c9baad42b7acb1d0ddaa540a0108fb7e3a8aaa0868f22f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b01ee5613f674231a1c9baad42b7acb1d0ddaa540a0108fb7e3a8aaa0868f22f","first_computed_at":"2026-07-05T06:01:26.101180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:26.101180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UKkbEmyuhO5K+QSVmie0R8s/SwS7KcAojfCk+KaC74dp1vc+Fta1U/E3L7Lu2uZGnE5A6laUw12DNpT9nHkECA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:26.101638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.07854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f79b1721e5d362a3c4f7606e7c31a4c48cfc79db7e05346f916ad19356cde46","sha256:d44e4ce02f19508df0681af0af408b56cd4001d119679875485369b4f313b770"],"state_sha256":"4ad345df6bcf851ade2fe87c976ab0b59a3f734eb99fc10380df4e76fd359e78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOf16pnJl8iJ23jh3gMwcd6CjlNCATl3oyMWCBS0t1Nm4zmyUlucqDH8br2N4ycBIEOeYkcdEboI68RY0cSxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:02:49.088803Z","bundle_sha256":"b4d4d1561df0de0647c86166a299da3fa6b99995a59cac2b7aa1b64c0c6da2f7"}}