{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UICX466VDJVQDIKKVCDWUBS7CZ","short_pith_number":"pith:UICX466V","canonical_record":{"source":{"id":"2408.10914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:58:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a50073349e04262d310ab81b8cae81e3376130d63cc21982124a38d125782e4","abstract_canon_sha256":"220ac55963eb1ce448f417274e5b7b57e93a03711c72dd2e15d149cc0595aafd"},"schema_version":"1.0"},"canonical_sha256":"a2057e7bd51a6b01a14aa8876a065f166a3628dfc1846c441b77b2c3875ed20f","source":{"kind":"arxiv","id":"2408.10914","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10914","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10914v1","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10914","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"UICX466VDJVQ","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"UICX466VDJVQDIKK","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"UICX466V","created_at":"2026-07-05T08:57:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UICX466VDJVQDIKKVCDWUBS7CZ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:58:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a50073349e04262d310ab81b8cae81e3376130d63cc21982124a38d125782e4","abstract_canon_sha256":"220ac55963eb1ce448f417274e5b7b57e93a03711c72dd2e15d149cc0595aafd"},"schema_version":"1.0"},"canonical_sha256":"a2057e7bd51a6b01a14aa8876a065f166a3628dfc1846c441b77b2c3875ed20f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:19.619883Z","signature_b64":"W9UKLmnFATLpFX5+9zYFF/mGDOKPDgygbiVkZV1fqtjS+VAmyswA6iG8Rc7N273HbKXK2zvabWGCdjEZyN8lAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2057e7bd51a6b01a14aa8876a065f166a3628dfc1846c441b77b2c3875ed20f","last_reissued_at":"2026-07-05T08:57:19.619489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:19.619489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10914","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":"2026-07-05T08:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q6L62SCDFz3ro+0VRdXbS+QbkXSs4s920HkTBI0IHUYsMU6S0k/iI8Aelm5ufsB4DNswm/8CB4YkBm35rOi8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:12:18.179820Z"},"content_sha256":"6170ec64febb7f39be9bfb1b9d8dba78acbcc065163d36e83daeae9dfd558c87","schema_version":"1.0","event_id":"sha256:6170ec64febb7f39be9bfb1b9d8dba78acbcc065163d36e83daeae9dfd558c87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UICX466VDJVQDIKKVCDWUBS7CZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Acyr Locatelli, Adrien Morisot, Ahmet \\\"Ust\\\"un, Ivan Zhang, Marzieh Fadaee, Raymond Ma, Sara Hooker, Viraat Aryabumi, Yixuan Su","submitted_at":"2024-08-20T14:58:13Z","abstract_excerpt":"Including code in the pre-training data mixture, even for models not specifically designed for code, has become a common practice in LLMs pre-training. While there has been anecdotal consensus among practitioners that code data plays a vital role in general LLMs' performance, there is only limited work analyzing the precise impact of code on non-code tasks. In this work, we systematically investigate the impact of code data on general performance. We ask \"what is the impact of code data used in pre-training on a large variety of downstream tasks beyond code generation\". We conduct extensive ab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10914","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/2408.10914/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":"2026-07-05T08:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DANrhfY8j8yNQiXXgm+y5+S0whuBXRJVGj3BgwIAJHFDuzdFvsGeuhcBI0MCPsHgq6UpunV8DiNL/5EDtgiRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:12:18.180180Z"},"content_sha256":"1ee3d3572d26a8220cf00467c30147a559e575901a0a346ad2859330b4335d53","schema_version":"1.0","event_id":"sha256:1ee3d3572d26a8220cf00467c30147a559e575901a0a346ad2859330b4335d53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UICX466VDJVQDIKKVCDWUBS7CZ/bundle.json","state_url":"https://pith.science/pith/UICX466VDJVQDIKKVCDWUBS7CZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UICX466VDJVQDIKKVCDWUBS7CZ/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":"2026-07-07T14:12:18Z","links":{"resolver":"https://pith.science/pith/UICX466VDJVQDIKKVCDWUBS7CZ","bundle":"https://pith.science/pith/UICX466VDJVQDIKKVCDWUBS7CZ/bundle.json","state":"https://pith.science/pith/UICX466VDJVQDIKKVCDWUBS7CZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UICX466VDJVQDIKKVCDWUBS7CZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UICX466VDJVQDIKKVCDWUBS7CZ","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":"220ac55963eb1ce448f417274e5b7b57e93a03711c72dd2e15d149cc0595aafd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:58:13Z","title_canon_sha256":"0a50073349e04262d310ab81b8cae81e3376130d63cc21982124a38d125782e4"},"schema_version":"1.0","source":{"id":"2408.10914","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10914","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10914v1","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10914","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"UICX466VDJVQ","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"UICX466VDJVQDIKK","created_at":"2026-07-05T08:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"UICX466V","created_at":"2026-07-05T08:57:19Z"}],"graph_snapshots":[{"event_id":"sha256:1ee3d3572d26a8220cf00467c30147a559e575901a0a346ad2859330b4335d53","target":"graph","created_at":"2026-07-05T08:57:19Z","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/2408.10914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Including code in the pre-training data mixture, even for models not specifically designed for code, has become a common practice in LLMs pre-training. While there has been anecdotal consensus among practitioners that code data plays a vital role in general LLMs' performance, there is only limited work analyzing the precise impact of code on non-code tasks. In this work, we systematically investigate the impact of code data on general performance. We ask \"what is the impact of code data used in pre-training on a large variety of downstream tasks beyond code generation\". We conduct extensive ab","authors_text":"Acyr Locatelli, Adrien Morisot, Ahmet \\\"Ust\\\"un, Ivan Zhang, Marzieh Fadaee, Raymond Ma, Sara Hooker, Viraat Aryabumi, Yixuan Su","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:58:13Z","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10914","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":"sha256:6170ec64febb7f39be9bfb1b9d8dba78acbcc065163d36e83daeae9dfd558c87","target":"record","created_at":"2026-07-05T08:57:19Z","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":"220ac55963eb1ce448f417274e5b7b57e93a03711c72dd2e15d149cc0595aafd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:58:13Z","title_canon_sha256":"0a50073349e04262d310ab81b8cae81e3376130d63cc21982124a38d125782e4"},"schema_version":"1.0","source":{"id":"2408.10914","kind":"arxiv","version":1}},"canonical_sha256":"a2057e7bd51a6b01a14aa8876a065f166a3628dfc1846c441b77b2c3875ed20f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2057e7bd51a6b01a14aa8876a065f166a3628dfc1846c441b77b2c3875ed20f","first_computed_at":"2026-07-05T08:57:19.619489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:19.619489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W9UKLmnFATLpFX5+9zYFF/mGDOKPDgygbiVkZV1fqtjS+VAmyswA6iG8Rc7N273HbKXK2zvabWGCdjEZyN8lAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:19.619883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10914","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6170ec64febb7f39be9bfb1b9d8dba78acbcc065163d36e83daeae9dfd558c87","sha256:1ee3d3572d26a8220cf00467c30147a559e575901a0a346ad2859330b4335d53"],"state_sha256":"31bdb698518a12604fe7ffb056596249974501711f6b49173224a33468c0b43b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MXcij4cOd7Kb/7u3HRT/pNaapit+/psbx0+fXtDtlfYBS7hHFqeGIshGYizUA2jaAkqHEed3rOeUxA9+fKLDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:12:18.182475Z","bundle_sha256":"f9cd5e3ad2969fde560fa483dd5e655e62574a8ced3d760ee074c7e02cad1f92"}}