{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MSPLMZYFJRNQ5XWKCNSTCYPYGF","short_pith_number":"pith:MSPLMZYF","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"},"canonical_sha256":"649eb667054c5b0edeca13653161f83154159f6958e96a4753a2cdc4eaf746e0","source":{"kind":"arxiv","id":"2405.19265","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19265","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19265v1","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19265","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"MSPLMZYFJRNQ","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"MSPLMZYFJRNQ5XWK","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"MSPLMZYF","created_at":"2026-07-05T10:08:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MSPLMZYFJRNQ5XWKCNSTCYPYGF","target":"record","payload":{"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"},"canonical_sha256":"649eb667054c5b0edeca13653161f83154159f6958e96a4753a2cdc4eaf746e0","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"},"source_kind":"arxiv","source_id":"2405.19265","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":"2026-07-05T10:08:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfAnpLi/WKKx2Av/eRtJq9W/LzqauVIgQGL2ep/trw+DRqoMReUwrxd1OxJ9+3P7aWI6kHDNPApULItUpZA1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:14:04.344562Z"},"content_sha256":"36d7ac203d8a4effcbbd9dd1ffadef5005198d20cfe56cb472460e055da08984","schema_version":"1.0","event_id":"sha256:36d7ac203d8a4effcbbd9dd1ffadef5005198d20cfe56cb472460e055da08984"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MSPLMZYFJRNQ5XWKCNSTCYPYGF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:08:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smgaLPIuSdKCwwWCJAuz6A2vZNTPXsVKtLOqa2uX100OVt0RsUp2PLztsTc6az2Ce29cT5jBlPN7GxLAInLsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:14:04.345225Z"},"content_sha256":"ca931aa907d967040fa04cebcb42c2a9806a819bcd1aaef0b616ed5818bb8946","schema_version":"1.0","event_id":"sha256:ca931aa907d967040fa04cebcb42c2a9806a819bcd1aaef0b616ed5818bb8946"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/bundle.json","state_url":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/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":"2026-08-19T09:14:04Z","links":{"resolver":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF","bundle":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/bundle.json","state":"https://pith.science/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSPLMZYFJRNQ5XWKCNSTCYPYGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MSPLMZYFJRNQ5XWKCNSTCYPYGF","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":"d6776a0334ad58385ee0a0473cde472c44dd719b97278e92f48aabce1af68944","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:57:33Z","title_canon_sha256":"f67f53770841ae14183e1e33bbfee4281ae879748dedf237cb404537058d0d5e"},"schema_version":"1.0","source":{"id":"2405.19265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19265","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19265v1","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19265","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"MSPLMZYFJRNQ","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"MSPLMZYFJRNQ5XWK","created_at":"2026-07-05T10:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"MSPLMZYF","created_at":"2026-07-05T10:08:17Z"}],"graph_snapshots":[{"event_id":"sha256:ca931aa907d967040fa04cebcb42c2a9806a819bcd1aaef0b616ed5818bb8946","target":"graph","created_at":"2026-07-05T10:08:17Z","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/2405.19265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cairong Zhao, Chengqi Lyu, Dahua Lin, Demin Song, Hang Yan, Kai Chen, Kuikun Liu, Qipeng Guo, Wenwei Zhang, Yudong Wang, Zifan Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:57:33Z","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19265","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":"sha256:36d7ac203d8a4effcbbd9dd1ffadef5005198d20cfe56cb472460e055da08984","target":"record","created_at":"2026-07-05T10:08:17Z","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":"d6776a0334ad58385ee0a0473cde472c44dd719b97278e92f48aabce1af68944","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:57:33Z","title_canon_sha256":"f67f53770841ae14183e1e33bbfee4281ae879748dedf237cb404537058d0d5e"},"schema_version":"1.0","source":{"id":"2405.19265","kind":"arxiv","version":1}},"canonical_sha256":"649eb667054c5b0edeca13653161f83154159f6958e96a4753a2cdc4eaf746e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"649eb667054c5b0edeca13653161f83154159f6958e96a4753a2cdc4eaf746e0","first_computed_at":"2026-07-05T10:08:17.451747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:17.451747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NFBmgmwpTNFDUL+ybmZUdMHPonhu0p4P9gykDNlbJLkCXmbbLD6byAb/ZnqAlAu/MXtLZtV6Ohc8QQfdyg1MAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:17.452165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36d7ac203d8a4effcbbd9dd1ffadef5005198d20cfe56cb472460e055da08984","sha256:ca931aa907d967040fa04cebcb42c2a9806a819bcd1aaef0b616ed5818bb8946"],"state_sha256":"2c1329cb0f7da57e329c04f9bf882f713c0db319a48505fafae0f294552ef9ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVRY6CzodSfLpsRllXlORrlEHyQ2Od7FtxmL7rxaNeRtDR/+BC5vuxDmuUwOxYzFYEBH798KEgLQwirsHs9lDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:14:04.352515Z","bundle_sha256":"334499f8621e2124c644c8dbe7218fa63eb800b717a4957ed245f1ee89a8b029"}}