{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:POXFCKP4TR7IOA6MILVBT5E3DL","short_pith_number":"pith:POXFCKP4","canonical_record":{"source":{"id":"2310.05492","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T07:56:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0fb75604f26716dd0c8fbe6a1c7437afc6a39260c08a54be57719d8de0f63052","abstract_canon_sha256":"57efea4453f8f163dba40b6902450e8cc1e9488e0f28af0179fad410ea5b457f"},"schema_version":"1.0"},"canonical_sha256":"7bae5129fc9c7e8703cc42ea19f49b1ac75b80ab4312b207dea607f631759975","source":{"kind":"arxiv","id":"2310.05492","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05492","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05492v4","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05492","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"POXFCKP4TR7I","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"POXFCKP4TR7IOA6M","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"POXFCKP4","created_at":"2026-07-05T08:28:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:POXFCKP4TR7IOA6MILVBT5E3DL","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05492","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T07:56:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0fb75604f26716dd0c8fbe6a1c7437afc6a39260c08a54be57719d8de0f63052","abstract_canon_sha256":"57efea4453f8f163dba40b6902450e8cc1e9488e0f28af0179fad410ea5b457f"},"schema_version":"1.0"},"canonical_sha256":"7bae5129fc9c7e8703cc42ea19f49b1ac75b80ab4312b207dea607f631759975","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:34.156910Z","signature_b64":"5c7OB6SLBnNxvngBqZKGKktQxyJvC78Sqzgw6DHWe2NIMR21fq0adUND1VcB/Bo0dVlwXRlpOG32V5TS98ukBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bae5129fc9c7e8703cc42ea19f49b1ac75b80ab4312b207dea607f631759975","last_reissued_at":"2026-07-05T08:28:34.156336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:34.156336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05492","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aGX0g+0uuQcR/ouu62yY0f87QxDLVq+4eXl6iLTanJ9B/i5OR4bx34CY+GmLBNSJ0UrPKpP60Foq0r5xhs7ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:06:09.106280Z"},"content_sha256":"a1f40d52ca184a030e0819006047b8899d353ce023c0e61063870166edc58061","schema_version":"1.0","event_id":"sha256:a1f40d52ca184a030e0819006047b8899d353ce023c0e61063870166edc58061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:POXFCKP4TR7IOA6MILVBT5E3DL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chang Zhou, Chengpeng Li, Dayiheng Liu, Guanting Dong, Hongyi Yuan, Jingren Zhou, Keming Lu, Mingfeng Xue, Wei Wang, Zheng Yuan","submitted_at":"2023-10-09T07:56:16Z","abstract_excerpt":"Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specifically focuses on the interplay of data composition between mathematical reasoning, code ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05492","kind":"arxiv","version":4},"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/2310.05492/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":"2026-07-05T08:28:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ghwr9s52bdEcSCROklr4ZkMLYL6ibHfSBMh9bN22be6JFjWSPTtq9z3Z23UcM8fhEvEKdnrUbH5EGUem2RC6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:06:09.106812Z"},"content_sha256":"173dcaaf4234bd03d72d965255ccfb811ede2163e843859043279dea5c1d5986","schema_version":"1.0","event_id":"sha256:173dcaaf4234bd03d72d965255ccfb811ede2163e843859043279dea5c1d5986"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POXFCKP4TR7IOA6MILVBT5E3DL/bundle.json","state_url":"https://pith.science/pith/POXFCKP4TR7IOA6MILVBT5E3DL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POXFCKP4TR7IOA6MILVBT5E3DL/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":"2026-08-07T18:06:09Z","links":{"resolver":"https://pith.science/pith/POXFCKP4TR7IOA6MILVBT5E3DL","bundle":"https://pith.science/pith/POXFCKP4TR7IOA6MILVBT5E3DL/bundle.json","state":"https://pith.science/pith/POXFCKP4TR7IOA6MILVBT5E3DL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POXFCKP4TR7IOA6MILVBT5E3DL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:POXFCKP4TR7IOA6MILVBT5E3DL","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":"57efea4453f8f163dba40b6902450e8cc1e9488e0f28af0179fad410ea5b457f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T07:56:16Z","title_canon_sha256":"0fb75604f26716dd0c8fbe6a1c7437afc6a39260c08a54be57719d8de0f63052"},"schema_version":"1.0","source":{"id":"2310.05492","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05492","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05492v4","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05492","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"POXFCKP4TR7I","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"POXFCKP4TR7IOA6M","created_at":"2026-07-05T08:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"POXFCKP4","created_at":"2026-07-05T08:28:34Z"}],"graph_snapshots":[{"event_id":"sha256:173dcaaf4234bd03d72d965255ccfb811ede2163e843859043279dea5c1d5986","target":"graph","created_at":"2026-07-05T08:28:34Z","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/2310.05492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specifically focuses on the interplay of data composition between mathematical reasoning, code ge","authors_text":"Chang Zhou, Chengpeng Li, Dayiheng Liu, Guanting Dong, Hongyi Yuan, Jingren Zhou, Keming Lu, Mingfeng Xue, Wei Wang, Zheng Yuan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05492","kind":"arxiv","version":4},"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:a1f40d52ca184a030e0819006047b8899d353ce023c0e61063870166edc58061","target":"record","created_at":"2026-07-05T08:28:34Z","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":"57efea4453f8f163dba40b6902450e8cc1e9488e0f28af0179fad410ea5b457f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T07:56:16Z","title_canon_sha256":"0fb75604f26716dd0c8fbe6a1c7437afc6a39260c08a54be57719d8de0f63052"},"schema_version":"1.0","source":{"id":"2310.05492","kind":"arxiv","version":4}},"canonical_sha256":"7bae5129fc9c7e8703cc42ea19f49b1ac75b80ab4312b207dea607f631759975","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bae5129fc9c7e8703cc42ea19f49b1ac75b80ab4312b207dea607f631759975","first_computed_at":"2026-07-05T08:28:34.156336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:34.156336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5c7OB6SLBnNxvngBqZKGKktQxyJvC78Sqzgw6DHWe2NIMR21fq0adUND1VcB/Bo0dVlwXRlpOG32V5TS98ukBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:34.156910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05492","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f40d52ca184a030e0819006047b8899d353ce023c0e61063870166edc58061","sha256:173dcaaf4234bd03d72d965255ccfb811ede2163e843859043279dea5c1d5986"],"state_sha256":"daf3e9c6acb508d8daa8ca2b488ce132edcfb22abdde50fbd1d6629343717ffd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wnbQ1mAnJ3v5upryCdKb2qUBmfgkpmjEpFI8rWWPEDQ3Kt+tqyVRKpqvKLtuZ1CIBSLbrXHiOSBHU7DPv+9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:06:09.112091Z","bundle_sha256":"e6c7b06c02c3cf066a1f027e22ce118ce6a4d8d904a0b3f9b77f26c37046f1db"}}