{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XBONA36K3DQO4P7NXHNESAM7TF","short_pith_number":"pith:XBONA36K","canonical_record":{"source":{"id":"2407.19705","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T05:00:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b47b972fad61f5c3ee459c67223e180641b0ff74afa7109e095e810f38018fcc","abstract_canon_sha256":"d86373c3455c1f8a6af3e0cdd7b547e6ebeb4d0e3019e5d16711218405b95f21"},"schema_version":"1.0"},"canonical_sha256":"b85cd06fcad8e0ee3fedb9da49019f995a658fa9972e707c3b53a472bc95fe70","source":{"kind":"arxiv","id":"2407.19705","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19705","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19705v3","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19705","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"XBONA36K3DQO","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"XBONA36K3DQO4P7N","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"XBONA36K","created_at":"2026-07-05T09:13:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XBONA36K3DQO4P7NXHNESAM7TF","target":"record","payload":{"canonical_record":{"source":{"id":"2407.19705","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T05:00:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b47b972fad61f5c3ee459c67223e180641b0ff74afa7109e095e810f38018fcc","abstract_canon_sha256":"d86373c3455c1f8a6af3e0cdd7b547e6ebeb4d0e3019e5d16711218405b95f21"},"schema_version":"1.0"},"canonical_sha256":"b85cd06fcad8e0ee3fedb9da49019f995a658fa9972e707c3b53a472bc95fe70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:06.288118Z","signature_b64":"4/hZOR/T5Bwrno8Fz4gvJoCMdOXqDNuL33yaiz+MNrSLWlU85EthY7Yk6TRW1uiNfnp5gp3t9fACc0dP0Tt5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b85cd06fcad8e0ee3fedb9da49019f995a658fa9972e707c3b53a472bc95fe70","last_reissued_at":"2026-07-05T09:13:06.287632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:06.287632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.19705","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":"2026-07-05T09:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ftOEANLN8M1gRpM2IzTJ58xatcKFk37Up6CzJzXLRkj3A9xzi+PxKH7eQORhrbKpevwJ0yoE1m0KD7m2jNFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:24:19.148197Z"},"content_sha256":"06ad1c68ff41fda79a03efc66684dd536ca249b2034a97925a4d51ace9d42df8","schema_version":"1.0","event_id":"sha256:06ad1c68ff41fda79a03efc66684dd536ca249b2034a97925a4d51ace9d42df8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XBONA36K3DQO4P7NXHNESAM7TF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hamid Alinejad-Rokny, Jingwei Zhu, Minghuan Tan, Min Yang, Ruixue Li","submitted_at":"2024-07-29T05:00:48Z","abstract_excerpt":"The rapid progress in Large Language Models (LLMs) has prompted the creation of numerous benchmarks to evaluate their capabilities.This study focuses on the Comprehensive Medical Benchmark in Chinese (CMB), showcasing how dataset diversity and distribution in supervised fine-tuning (SFT) may enhance LLM performance.Remarkably, We successfully trained a smaller base model to achieve scores comparable to larger models, indicating that a diverse and well-distributed dataset can optimize performance regardless of model size.This study suggests that even smaller models may reach high performance le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19705","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/2407.19705/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":"2026-07-05T09:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6mf0f7phD3JOcii+Oed9bd18jZd9y54nMww2U9kNbmC+X7WXO1+iGDi17xLK1rhMf5t6XYdhaKV7SesTaw7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:24:19.150483Z"},"content_sha256":"19d01e51abdc72fc2f6199115a5404ad51f0e0a06b698a941a77b8dfb36cbf9a","schema_version":"1.0","event_id":"sha256:19d01e51abdc72fc2f6199115a5404ad51f0e0a06b698a941a77b8dfb36cbf9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBONA36K3DQO4P7NXHNESAM7TF/bundle.json","state_url":"https://pith.science/pith/XBONA36K3DQO4P7NXHNESAM7TF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBONA36K3DQO4P7NXHNESAM7TF/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":"2026-08-18T14:24:19Z","links":{"resolver":"https://pith.science/pith/XBONA36K3DQO4P7NXHNESAM7TF","bundle":"https://pith.science/pith/XBONA36K3DQO4P7NXHNESAM7TF/bundle.json","state":"https://pith.science/pith/XBONA36K3DQO4P7NXHNESAM7TF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBONA36K3DQO4P7NXHNESAM7TF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XBONA36K3DQO4P7NXHNESAM7TF","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":"d86373c3455c1f8a6af3e0cdd7b547e6ebeb4d0e3019e5d16711218405b95f21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T05:00:48Z","title_canon_sha256":"b47b972fad61f5c3ee459c67223e180641b0ff74afa7109e095e810f38018fcc"},"schema_version":"1.0","source":{"id":"2407.19705","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19705","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19705v3","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19705","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"XBONA36K3DQO","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"XBONA36K3DQO4P7N","created_at":"2026-07-05T09:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"XBONA36K","created_at":"2026-07-05T09:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:19d01e51abdc72fc2f6199115a5404ad51f0e0a06b698a941a77b8dfb36cbf9a","target":"graph","created_at":"2026-07-05T09:13:06Z","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/2407.19705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress in Large Language Models (LLMs) has prompted the creation of numerous benchmarks to evaluate their capabilities.This study focuses on the Comprehensive Medical Benchmark in Chinese (CMB), showcasing how dataset diversity and distribution in supervised fine-tuning (SFT) may enhance LLM performance.Remarkably, We successfully trained a smaller base model to achieve scores comparable to larger models, indicating that a diverse and well-distributed dataset can optimize performance regardless of model size.This study suggests that even smaller models may reach high performance le","authors_text":"Hamid Alinejad-Rokny, Jingwei Zhu, Minghuan Tan, Min Yang, Ruixue Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T05:00:48Z","title":"CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19705","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":"sha256:06ad1c68ff41fda79a03efc66684dd536ca249b2034a97925a4d51ace9d42df8","target":"record","created_at":"2026-07-05T09:13:06Z","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":"d86373c3455c1f8a6af3e0cdd7b547e6ebeb4d0e3019e5d16711218405b95f21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T05:00:48Z","title_canon_sha256":"b47b972fad61f5c3ee459c67223e180641b0ff74afa7109e095e810f38018fcc"},"schema_version":"1.0","source":{"id":"2407.19705","kind":"arxiv","version":3}},"canonical_sha256":"b85cd06fcad8e0ee3fedb9da49019f995a658fa9972e707c3b53a472bc95fe70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b85cd06fcad8e0ee3fedb9da49019f995a658fa9972e707c3b53a472bc95fe70","first_computed_at":"2026-07-05T09:13:06.287632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:06.287632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4/hZOR/T5Bwrno8Fz4gvJoCMdOXqDNuL33yaiz+MNrSLWlU85EthY7Yk6TRW1uiNfnp5gp3t9fACc0dP0Tt5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:06.288118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19705","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06ad1c68ff41fda79a03efc66684dd536ca249b2034a97925a4d51ace9d42df8","sha256:19d01e51abdc72fc2f6199115a5404ad51f0e0a06b698a941a77b8dfb36cbf9a"],"state_sha256":"36eb8f3e14a9a0ab4380c1615ec365e5394fe735d9ba1b0b311d49ac7722fb6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"79PYIbBBo9cArW/AbH22Q6ZnSgwZCgjJxJF+nMQIAFJH87dp4bRBvSjSDWFsPlDS3XgQi+ypqdqVRh25BYXPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:24:19.177546Z","bundle_sha256":"6fde7ac372cab3214db614c8870540120d870d2e8ccda06bb9ee96befde6b5ce"}}