{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZSKEYYXR5WBZOWD22F6IO5FPPD","short_pith_number":"pith:ZSKEYYXR","canonical_record":{"source":{"id":"2403.00338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T08:05:44Z","cross_cats_sorted":[],"title_canon_sha256":"4567f7ce6b9d59bac571b5c31f146748ab07989c96b696973801da2905410b5d","abstract_canon_sha256":"03e70a5017ba9185cda865a22d5f2983f05a074815c218f69d787512c829294f"},"schema_version":"1.0"},"canonical_sha256":"cc944c62f1ed8397587ad17c8774af78c5119466f5f36685aaf50e2e86aea50a","source":{"kind":"arxiv","id":"2403.00338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00338","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00338v1","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00338","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZSKEYYXR5WBZ","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZSKEYYXR5WBZOWD2","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZSKEYYXR","created_at":"2026-07-05T07:51:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZSKEYYXR5WBZOWD22F6IO5FPPD","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T08:05:44Z","cross_cats_sorted":[],"title_canon_sha256":"4567f7ce6b9d59bac571b5c31f146748ab07989c96b696973801da2905410b5d","abstract_canon_sha256":"03e70a5017ba9185cda865a22d5f2983f05a074815c218f69d787512c829294f"},"schema_version":"1.0"},"canonical_sha256":"cc944c62f1ed8397587ad17c8774af78c5119466f5f36685aaf50e2e86aea50a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:02.692484Z","signature_b64":"Vd5lkVQU8Spdn5PN5XYz2QjkyZpOiG56u4kx9lVPHcKkompNxQMNDHfKiVXHXCM9DGabcBCXJynqVsOLRVZ0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc944c62f1ed8397587ad17c8774af78c5119466f5f36685aaf50e2e86aea50a","last_reissued_at":"2026-07-05T07:51:02.691958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:02.691958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00338","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":"2026-07-05T07:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZazOuaTc+d6P86m456OtYkEvKkTphKxUuInM2aeoJZIoIro7QghQZyNlbn4oUiko62+FLAlDtA0JoRMjjeBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:21:55.036201Z"},"content_sha256":"88485aab9571b3badad40961e422573536bc5065027a24e706d69521f909bd2a","schema_version":"1.0","event_id":"sha256:88485aab9571b3badad40961e422573536bc5065027a24e706d69521f909bd2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZSKEYYXR5WBZOWD22F6IO5FPPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongliang Xu, Qingfu Zhu, Qing Yang, Wanxiang Che, Xianzhen Luo, Xu Wang, Zhiming Zhang","submitted_at":"2024-03-01T08:05:44Z","abstract_excerpt":"Instruction tuning plays a pivotal role in Code Large Language Models (Code LLMs) for the task of program synthesis. Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated). Natural-instruct includes diverse and correct codes but lacks instruction-code pairs, and exists improper code formats like nested single-line codes. In contrast, self-instruct automatically generates proper paired data. However, it suffers from low diversity due to generating duplicates and cannot ensure the correctness of codes. To brid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00338","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/2403.00338/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":"2026-07-05T07:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K90oqYA80XyqyuO4CtLZOhtVWp0UdJwUoszD0wVaBCekgkfIKzRqJ5wrUX2zi0wWnm7+WfjweUIqhDrCwdkTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:21:55.037060Z"},"content_sha256":"627e8fec8f370e3ef52844cf01f28ff68bcab8f0e607dec1067d86dfbfe03953","schema_version":"1.0","event_id":"sha256:627e8fec8f370e3ef52844cf01f28ff68bcab8f0e607dec1067d86dfbfe03953"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD/bundle.json","state_url":"https://pith.science/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD/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":"2026-08-17T18:21:55Z","links":{"resolver":"https://pith.science/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD","bundle":"https://pith.science/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD/bundle.json","state":"https://pith.science/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSKEYYXR5WBZOWD22F6IO5FPPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZSKEYYXR5WBZOWD22F6IO5FPPD","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":"03e70a5017ba9185cda865a22d5f2983f05a074815c218f69d787512c829294f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T08:05:44Z","title_canon_sha256":"4567f7ce6b9d59bac571b5c31f146748ab07989c96b696973801da2905410b5d"},"schema_version":"1.0","source":{"id":"2403.00338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00338","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00338v1","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00338","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZSKEYYXR5WBZ","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZSKEYYXR5WBZOWD2","created_at":"2026-07-05T07:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZSKEYYXR","created_at":"2026-07-05T07:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:627e8fec8f370e3ef52844cf01f28ff68bcab8f0e607dec1067d86dfbfe03953","target":"graph","created_at":"2026-07-05T07:51:02Z","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/2403.00338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning plays a pivotal role in Code Large Language Models (Code LLMs) for the task of program synthesis. Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated). Natural-instruct includes diverse and correct codes but lacks instruction-code pairs, and exists improper code formats like nested single-line codes. In contrast, self-instruct automatically generates proper paired data. However, it suffers from low diversity due to generating duplicates and cannot ensure the correctness of codes. To brid","authors_text":"Dongliang Xu, Qingfu Zhu, Qing Yang, Wanxiang Che, Xianzhen Luo, Xu Wang, Zhiming Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T08:05:44Z","title":"Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00338","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":"sha256:88485aab9571b3badad40961e422573536bc5065027a24e706d69521f909bd2a","target":"record","created_at":"2026-07-05T07:51:02Z","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":"03e70a5017ba9185cda865a22d5f2983f05a074815c218f69d787512c829294f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T08:05:44Z","title_canon_sha256":"4567f7ce6b9d59bac571b5c31f146748ab07989c96b696973801da2905410b5d"},"schema_version":"1.0","source":{"id":"2403.00338","kind":"arxiv","version":1}},"canonical_sha256":"cc944c62f1ed8397587ad17c8774af78c5119466f5f36685aaf50e2e86aea50a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc944c62f1ed8397587ad17c8774af78c5119466f5f36685aaf50e2e86aea50a","first_computed_at":"2026-07-05T07:51:02.691958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:02.691958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vd5lkVQU8Spdn5PN5XYz2QjkyZpOiG56u4kx9lVPHcKkompNxQMNDHfKiVXHXCM9DGabcBCXJynqVsOLRVZ0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:02.692484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88485aab9571b3badad40961e422573536bc5065027a24e706d69521f909bd2a","sha256:627e8fec8f370e3ef52844cf01f28ff68bcab8f0e607dec1067d86dfbfe03953"],"state_sha256":"290aad6d75f0ad034c7ff0d5032219e46ed2a882c60b82409810b56c2b0a57a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jePzzQ1HxRQh6gdcSWmYOr0HtV+EpUEyY+w1CbCH+pSMfUPL1FpLw9E6Pf9K0XaCjJUTAJT3O0rKjoPBZDrcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:21:55.049771Z","bundle_sha256":"ae22f8a286c43419a21383217a8ad19cf57232eb72454b570cab5d7f93c596fc"}}