{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AJJMHSJTGDGKZIYFXGPSG6YYHS","short_pith_number":"pith:AJJMHSJT","canonical_record":{"source":{"id":"2405.20535","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T23:20:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d96cf0a6acd858424609af014e4a65d934fff840bdfa991adce33bdfce402919","abstract_canon_sha256":"82724fc2a7209d572bf7c415eaacb8754b84f66489451cf8ab80874d5979871d"},"schema_version":"1.0"},"canonical_sha256":"0252c3c93330ccaca305b99f237b183cb5d2e0b330b63ecf308debf750f41f6a","source":{"kind":"arxiv","id":"2405.20535","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20535","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20535v2","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20535","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"AJJMHSJTGDGK","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"AJJMHSJTGDGKZIYF","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"AJJMHSJT","created_at":"2026-07-05T09:48:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AJJMHSJTGDGKZIYFXGPSG6YYHS","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20535","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T23:20:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d96cf0a6acd858424609af014e4a65d934fff840bdfa991adce33bdfce402919","abstract_canon_sha256":"82724fc2a7209d572bf7c415eaacb8754b84f66489451cf8ab80874d5979871d"},"schema_version":"1.0"},"canonical_sha256":"0252c3c93330ccaca305b99f237b183cb5d2e0b330b63ecf308debf750f41f6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:13.796259Z","signature_b64":"9Xig03U/NtT3XMLPPoJOXPTG50aNh+EKX3y3BkjF7VfeHYT7W71g1rb/82KugOdxY6ceKnebtOxgWcJ1vWvHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0252c3c93330ccaca305b99f237b183cb5d2e0b330b63ecf308debf750f41f6a","last_reissued_at":"2026-07-05T09:48:13.795744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:13.795744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20535","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LviIpPoazAMhisWaAlm46QTMar/3UE1UEFz2sIBFpmXYx+hnTjfjD9Ptx4lN7mzxlmcwR/xsn92OY5GVmiKvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T01:37:33.018778Z"},"content_sha256":"d47478a3177af5c05a25af0dd86e1a24ed1336c9b40695a525f8c1c9490e4615","schema_version":"1.0","event_id":"sha256:d47478a3177af5c05a25af0dd86e1a24ed1336c9b40695a525f8c1c9490e4615"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AJJMHSJTGDGKZIYFXGPSG6YYHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Lichang Chen, Linda Ruth Petzold, William Yang Wang, Xianjun Yang, Xinlu Zhang, Xi Ye, Zhiyu Zoey Chen","submitted_at":"2024-05-30T23:20:25Z","abstract_excerpt":"Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilities during pretraining, its role in activating internal reasoning capacities during IFT remains understudied. This paper investigates a key question: How does coding data impact LLMs' reasoning capacities during IFT stage? To explore this, we thoroughly examine the impact of coding data across different coding data proportions, model families, sizes, and reasoning domains, from various perspectives. Specifically, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20535","kind":"arxiv","version":2},"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/2405.20535/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":"2026-07-05T09:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/VHGk1Uy6/EDwe+xuJdUlsHpBaXAz+JfX8AAWFcvvF2008R/GfQUJdhAmstYnMulLXK3RVDyL/s9raqC99VAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T01:37:33.019157Z"},"content_sha256":"1160842ef00b3320ddb349edf57c296ed73e12e016c5d7e2d122739366f7246c","schema_version":"1.0","event_id":"sha256:1160842ef00b3320ddb349edf57c296ed73e12e016c5d7e2d122739366f7246c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS/bundle.json","state_url":"https://pith.science/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS/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":"2026-07-25T01:37:33Z","links":{"resolver":"https://pith.science/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS","bundle":"https://pith.science/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS/bundle.json","state":"https://pith.science/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJJMHSJTGDGKZIYFXGPSG6YYHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AJJMHSJTGDGKZIYFXGPSG6YYHS","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":"82724fc2a7209d572bf7c415eaacb8754b84f66489451cf8ab80874d5979871d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T23:20:25Z","title_canon_sha256":"d96cf0a6acd858424609af014e4a65d934fff840bdfa991adce33bdfce402919"},"schema_version":"1.0","source":{"id":"2405.20535","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20535","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20535v2","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20535","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"AJJMHSJTGDGK","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"AJJMHSJTGDGKZIYF","created_at":"2026-07-05T09:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"AJJMHSJT","created_at":"2026-07-05T09:48:13Z"}],"graph_snapshots":[{"event_id":"sha256:1160842ef00b3320ddb349edf57c296ed73e12e016c5d7e2d122739366f7246c","target":"graph","created_at":"2026-07-05T09:48:13Z","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/2405.20535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilities during pretraining, its role in activating internal reasoning capacities during IFT remains understudied. This paper investigates a key question: How does coding data impact LLMs' reasoning capacities during IFT stage? To explore this, we thoroughly examine the impact of coding data across different coding data proportions, model families, sizes, and reasoning domains, from various perspectives. Specifically, we ","authors_text":"Lichang Chen, Linda Ruth Petzold, William Yang Wang, Xianjun Yang, Xinlu Zhang, Xi Ye, Zhiyu Zoey Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T23:20:25Z","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20535","kind":"arxiv","version":2},"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:d47478a3177af5c05a25af0dd86e1a24ed1336c9b40695a525f8c1c9490e4615","target":"record","created_at":"2026-07-05T09:48:13Z","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":"82724fc2a7209d572bf7c415eaacb8754b84f66489451cf8ab80874d5979871d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T23:20:25Z","title_canon_sha256":"d96cf0a6acd858424609af014e4a65d934fff840bdfa991adce33bdfce402919"},"schema_version":"1.0","source":{"id":"2405.20535","kind":"arxiv","version":2}},"canonical_sha256":"0252c3c93330ccaca305b99f237b183cb5d2e0b330b63ecf308debf750f41f6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0252c3c93330ccaca305b99f237b183cb5d2e0b330b63ecf308debf750f41f6a","first_computed_at":"2026-07-05T09:48:13.795744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:13.795744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Xig03U/NtT3XMLPPoJOXPTG50aNh+EKX3y3BkjF7VfeHYT7W71g1rb/82KugOdxY6ceKnebtOxgWcJ1vWvHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:13.796259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20535","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d47478a3177af5c05a25af0dd86e1a24ed1336c9b40695a525f8c1c9490e4615","sha256:1160842ef00b3320ddb349edf57c296ed73e12e016c5d7e2d122739366f7246c"],"state_sha256":"f9956c332569e7cfbe9c68f607d61b5adb8a343be955a3872fe118dc65554377"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxjjoD4AAH0kagGdm66YSmtoyQgiR1i/kWCbfHe3h+RFmxM+wCGSr3wOEju7s/qlO54Pg5urbbCwBFobQqE1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T01:37:33.021328Z","bundle_sha256":"dca9f147e26b0206e0d1fb463cc188dd3b0d689459b23c0ba5c00c01dbd7f5dd"}}