{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MSPLMZYFJRNQ5XWKCNSTCYPYGF","short_pith_number":"pith:MSPLMZYF","schema_version":"1.0","canonical_sha256":"649eb667054c5b0edeca13653161f83154159f6958e96a4753a2cdc4eaf746e0","source":{"kind":"arxiv","id":"2405.19265","version":1},"attestation_state":"computed","paper":{"title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cairong Zhao, Chengqi Lyu, Dahua Lin, Demin Song, Hang Yan, Kai Chen, Kuikun Liu, Qipeng Guo, Wenwei Zhang, Yudong Wang, Zifan Song","submitted_at":"2024-05-29T16:57:33Z","abstract_excerpt":"Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance. However, previous Code LLMs are typically fine-tuned on single-source data with limited quality and diversity, which may insufficiently elicit the potential of pre-trained Code LLMs. In this paper, we present AlchemistCoder, a series of Code LLMs with enhanced code generation and generalization capabilities fine-tuned on multi-source data. To achieve this, we pioneer to unveil inherent conflicts among the various styles and qualities in multi-source c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.19265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:57:33Z","cross_cats_sorted":[],"title_canon_sha256":"f67f53770841ae14183e1e33bbfee4281ae879748dedf237cb404537058d0d5e","abstract_canon_sha256":"d6776a0334ad58385ee0a0473cde472c44dd719b97278e92f48aabce1af68944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:17.452165Z","signature_b64":"NFBmgmwpTNFDUL+ybmZUdMHPonhu0p4P9gykDNlbJLkCXmbbLD6byAb/ZnqAlAu/MXtLZtV6Ohc8QQfdyg1MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"649eb667054c5b0edeca13653161f83154159f6958e96a4753a2cdc4eaf746e0","last_reissued_at":"2026-07-05T10:08:17.451747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:17.451747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cairong Zhao, Chengqi Lyu, Dahua Lin, Demin Song, Hang Yan, Kai Chen, Kuikun Liu, Qipeng Guo, Wenwei Zhang, Yudong Wang, Zifan Song","submitted_at":"2024-05-29T16:57:33Z","abstract_excerpt":"Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance. However, previous Code LLMs are typically fine-tuned on single-source data with limited quality and diversity, which may insufficiently elicit the potential of pre-trained Code LLMs. In this paper, we present AlchemistCoder, a series of Code LLMs with enhanced code generation and generalization capabilities fine-tuned on multi-source data. To achieve this, we pioneer to unveil inherent conflicts among the various styles and qualities in multi-source c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19265","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/2405.19265/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.19265","created_at":"2026-07-05T10:08:17.451803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19265v1","created_at":"2026-07-05T10:08:17.451803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19265","created_at":"2026-07-05T10:08:17.451803+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSPLMZYFJRNQ","created_at":"2026-07-05T10:08:17.451803+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSPLMZYFJRNQ5XWK","created_at":"2026-07-05T10:08:17.451803+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSPLMZYF","created_at":"2026-07-05T10:08:17.451803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07858","citing_title":"SCoder: Iterative Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF","json":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF.json","graph_json":"https://pith.science/api/pith-number/MSPLMZYFJRNQ5XWKCNSTCYPYGF/graph.json","events_json":"https://pith.science/api/pith-number/MSPLMZYFJRNQ5XWKCNSTCYPYGF/events.json","paper":"https://pith.science/paper/MSPLMZYF"},"agent_actions":{"view_html":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF","download_json":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF.json","view_paper":"https://pith.science/paper/MSPLMZYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19265&json=true","fetch_graph":"https://pith.science/api/pith-number/MSPLMZYFJRNQ5XWKCNSTCYPYGF/graph.json","fetch_events":"https://pith.science/api/pith-number/MSPLMZYFJRNQ5XWKCNSTCYPYGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/action/storage_attestation","attest_author":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/action/author_attestation","sign_citation":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/action/citation_signature","submit_replication":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/action/replication_record"}},"created_at":"2026-07-05T10:08:17.451803+00:00","updated_at":"2026-07-05T10:08:17.451803+00:00"}