{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:57AVIGJWM6RQH4JX5TABZD3D6M","short_pith_number":"pith:57AVIGJW","canonical_record":{"source":{"id":"2407.05700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T08:00:05Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"16e3d1122ef9b081fcb5316e5a8afb2467dc23fcf42a386d49379caedc3fb502","abstract_canon_sha256":"32659e57748f776fd469037c4b39d8a311407d8d930e45a9ac52d64293d6543a"},"schema_version":"1.0"},"canonical_sha256":"efc154193667a303f137ecc01c8f63f33eeedf45cd2687073e276ae9fa86205b","source":{"kind":"arxiv","id":"2407.05700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05700","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05700v2","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05700","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"57AVIGJWM6RQ","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"57AVIGJWM6RQH4JX","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"57AVIGJW","created_at":"2026-07-05T09:49:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:57AVIGJWM6RQH4JX5TABZD3D6M","target":"record","payload":{"canonical_record":{"source":{"id":"2407.05700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T08:00:05Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"16e3d1122ef9b081fcb5316e5a8afb2467dc23fcf42a386d49379caedc3fb502","abstract_canon_sha256":"32659e57748f776fd469037c4b39d8a311407d8d930e45a9ac52d64293d6543a"},"schema_version":"1.0"},"canonical_sha256":"efc154193667a303f137ecc01c8f63f33eeedf45cd2687073e276ae9fa86205b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:07.471851Z","signature_b64":"CUCZwkHkrac7AGFNyljcoDxl1ElnuF1JUVAb6kPDjs7EiKiWZh8fHEHxa4o5DZaPGpJgtYZiaNh06P8aLGZoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc154193667a303f137ecc01c8f63f33eeedf45cd2687073e276ae9fa86205b","last_reissued_at":"2026-07-05T09:49:07.471351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:07.471351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.05700","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":"2026-07-05T09:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fx9h2Fysmtll95Xwk5ef8dmWFnGhKEXGIGtJMm4RZuNrEz2LYDn73CqDvdDZTvR4dQ5XKjb+C+ZmplQZF+RkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:38:49.040264Z"},"content_sha256":"1a18556ea1d8a18c04980ba35305c6706f7e8e265c285c232999970d1d7fb47b","schema_version":"1.0","event_id":"sha256:1a18556ea1d8a18c04980ba35305c6706f7e8e265c285c232999970d1d7fb47b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:57AVIGJWM6RQH4JX5TABZD3D6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Di Huang, Kaizhao Yuan, Lingzhe Gao, Qi Guo, Rui Zhang, Shihao Liu, Wei Wang, Wenxuan Shi, Xing Hu, Xishan Zhang, Yewen Pu, Yunji Chen, Yutong Wu, Zidong Du, Ziyuan Nan","submitted_at":"2024-07-08T08:00:05Z","abstract_excerpt":"Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset. We make two observations: (1) A code snippet can serve as the response to different instructions. (2) Instruction-tuned code LLMs perform better at translating code into instructions than the reverse. Based on these observations, we propose Inverse-Instruct, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05700","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/2407.05700/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":"2026-07-05T09:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMWejYXPDY2ii4o3Xbw2NJt5i163MQpDGJq1U0jsQu2B/R5z3tyslSPQGlcMHc6ndow2c/57NzprQ6wTw+gmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:38:49.040907Z"},"content_sha256":"237bff310834dec0c72da86a71202d8465637094c03545782c20f6278c50f112","schema_version":"1.0","event_id":"sha256:237bff310834dec0c72da86a71202d8465637094c03545782c20f6278c50f112"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57AVIGJWM6RQH4JX5TABZD3D6M/bundle.json","state_url":"https://pith.science/pith/57AVIGJWM6RQH4JX5TABZD3D6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57AVIGJWM6RQH4JX5TABZD3D6M/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":"2026-07-07T06:38:49Z","links":{"resolver":"https://pith.science/pith/57AVIGJWM6RQH4JX5TABZD3D6M","bundle":"https://pith.science/pith/57AVIGJWM6RQH4JX5TABZD3D6M/bundle.json","state":"https://pith.science/pith/57AVIGJWM6RQH4JX5TABZD3D6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57AVIGJWM6RQH4JX5TABZD3D6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:57AVIGJWM6RQH4JX5TABZD3D6M","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":"32659e57748f776fd469037c4b39d8a311407d8d930e45a9ac52d64293d6543a","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T08:00:05Z","title_canon_sha256":"16e3d1122ef9b081fcb5316e5a8afb2467dc23fcf42a386d49379caedc3fb502"},"schema_version":"1.0","source":{"id":"2407.05700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05700","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05700v2","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05700","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"57AVIGJWM6RQ","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"57AVIGJWM6RQH4JX","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"57AVIGJW","created_at":"2026-07-05T09:49:07Z"}],"graph_snapshots":[{"event_id":"sha256:237bff310834dec0c72da86a71202d8465637094c03545782c20f6278c50f112","target":"graph","created_at":"2026-07-05T09:49:07Z","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/2407.05700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset. We make two observations: (1) A code snippet can serve as the response to different instructions. (2) Instruction-tuned code LLMs perform better at translating code into instructions than the reverse. Based on these observations, we propose Inverse-Instruct, a","authors_text":"Dawei Yin, Di Huang, Kaizhao Yuan, Lingzhe Gao, Qi Guo, Rui Zhang, Shihao Liu, Wei Wang, Wenxuan Shi, Xing Hu, Xishan Zhang, Yewen Pu, Yunji Chen, Yutong Wu, Zidong Du, Ziyuan Nan","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T08:00:05Z","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05700","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":"sha256:1a18556ea1d8a18c04980ba35305c6706f7e8e265c285c232999970d1d7fb47b","target":"record","created_at":"2026-07-05T09:49:07Z","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":"32659e57748f776fd469037c4b39d8a311407d8d930e45a9ac52d64293d6543a","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T08:00:05Z","title_canon_sha256":"16e3d1122ef9b081fcb5316e5a8afb2467dc23fcf42a386d49379caedc3fb502"},"schema_version":"1.0","source":{"id":"2407.05700","kind":"arxiv","version":2}},"canonical_sha256":"efc154193667a303f137ecc01c8f63f33eeedf45cd2687073e276ae9fa86205b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efc154193667a303f137ecc01c8f63f33eeedf45cd2687073e276ae9fa86205b","first_computed_at":"2026-07-05T09:49:07.471351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:07.471351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CUCZwkHkrac7AGFNyljcoDxl1ElnuF1JUVAb6kPDjs7EiKiWZh8fHEHxa4o5DZaPGpJgtYZiaNh06P8aLGZoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:07.471851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a18556ea1d8a18c04980ba35305c6706f7e8e265c285c232999970d1d7fb47b","sha256:237bff310834dec0c72da86a71202d8465637094c03545782c20f6278c50f112"],"state_sha256":"cba1f78a79b387f50a1e2a852d8cfb32c4276f7e920d15f1b55efda6e719b8d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L7M5PUmaFk0BN6ZH0ctyViuVpmXO5Dc3ZOIYlkUSmXxFAm/8K43Qjo7VSdEQ5DOyOCuJhLJDSEEet/ET2WZdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:38:49.044051Z","bundle_sha256":"761cb2527d243c17c76760cfa44cd89e4d9527fe8f9d1562aa1e04fd848483ed"}}