{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OGGGZMYZB2PZU23YBW4NURVGBW","short_pith_number":"pith:OGGGZMYZ","canonical_record":{"source":{"id":"2310.10508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-10-11T00:21:00Z","cross_cats_sorted":[],"title_canon_sha256":"f01f4cfbae37a2b15c272b677fa48977827319954128e8351f5944081395f21f","abstract_canon_sha256":"5ee756fda3e4b4cdabfea7aebeaa6c38587ab53421666634461f31747f03b5d6"},"schema_version":"1.0"},"canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","source":{"kind":"arxiv","id":"2310.10508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10508","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10508v2","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10508","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"OGGGZMYZB2PZ","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"pith_short_16","alias_value":"OGGGZMYZB2PZU23Y","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"pith_short_8","alias_value":"OGGGZMYZ","created_at":"2026-07-05T10:17:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OGGGZMYZB2PZU23YBW4NURVGBW","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-10-11T00:21:00Z","cross_cats_sorted":[],"title_canon_sha256":"f01f4cfbae37a2b15c272b677fa48977827319954128e8351f5944081395f21f","abstract_canon_sha256":"5ee756fda3e4b4cdabfea7aebeaa6c38587ab53421666634461f31747f03b5d6"},"schema_version":"1.0"},"canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:05.474939Z","signature_b64":"DgovR6mR/rBisoY7V39amPi4Jmx1oSfi9g7Xp/1GqUUF53YbtTB11stCW+Bv18p/xYURHP8t7/qq8gezq18rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","last_reissued_at":"2026-07-05T10:17:05.474449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:05.474449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10508","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":"2026-07-05T10:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qS7PMValbbX0xIO7WEjbEiCQlahaI2MFWJoY7MD1OijvmO6srGx51AT9k+2+ahH0mRNCNfIlbQJjyOuO9FqUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:26:14.846702Z"},"content_sha256":"c18f1213dbd78a6c7e8cf75272fc5e37738426a0caf6d168ffc247cafc567631","schema_version":"1.0","event_id":"sha256:c18f1213dbd78a6c7e8cf75272fc5e37738426a0caf6d168ffc247cafc567631"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OGGGZMYZB2PZU23YBW4NURVGBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Clark Tang, Hadi Hemmati, Jiho Shin, Maleknaz Nayebi, Song Wang, Tahmineh Mohati","submitted_at":"2023-10-11T00:21:00Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves applying different strategies to query LLMs, like ChatGPT, while fine-tuning further adapts pre-trained models, such as CodeBERT, by training them on task-specific data. Despite the growth in the area, there remains a lack of comprehensive comparative analysis between the approaches for code models. In this paper, we evaluate GPT-4 using three prompt enginee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10508","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/2310.10508/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":"2026-07-05T10:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nukBfdHp/fpb6sZdXuoif3sVdqLnIP5rjAh1NedUq5TLakwjAuphoweyXKBwbtIix2/CNmkY3INOG6cZFdLLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:26:14.847568Z"},"content_sha256":"0c49d03a1f426720b63304a06537fb1cb63b1894b984ea9985295e29f14d02f8","schema_version":"1.0","event_id":"sha256:0c49d03a1f426720b63304a06537fb1cb63b1894b984ea9985295e29f14d02f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/bundle.json","state_url":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OGGGZMYZB2PZU23YBW4NURVGBW/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":"2026-08-10T11:26:14Z","links":{"resolver":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW","bundle":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/bundle.json","state":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OGGGZMYZB2PZU23YBW4NURVGBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OGGGZMYZB2PZU23YBW4NURVGBW","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":"5ee756fda3e4b4cdabfea7aebeaa6c38587ab53421666634461f31747f03b5d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-10-11T00:21:00Z","title_canon_sha256":"f01f4cfbae37a2b15c272b677fa48977827319954128e8351f5944081395f21f"},"schema_version":"1.0","source":{"id":"2310.10508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10508","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10508v2","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10508","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"OGGGZMYZB2PZ","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"pith_short_16","alias_value":"OGGGZMYZB2PZU23Y","created_at":"2026-07-05T10:17:05Z"},{"alias_kind":"pith_short_8","alias_value":"OGGGZMYZ","created_at":"2026-07-05T10:17:05Z"}],"graph_snapshots":[{"event_id":"sha256:0c49d03a1f426720b63304a06537fb1cb63b1894b984ea9985295e29f14d02f8","target":"graph","created_at":"2026-07-05T10:17:05Z","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/2310.10508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves applying different strategies to query LLMs, like ChatGPT, while fine-tuning further adapts pre-trained models, such as CodeBERT, by training them on task-specific data. Despite the growth in the area, there remains a lack of comprehensive comparative analysis between the approaches for code models. In this paper, we evaluate GPT-4 using three prompt enginee","authors_text":"Clark Tang, Hadi Hemmati, Jiho Shin, Maleknaz Nayebi, Song Wang, Tahmineh Mohati","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-10-11T00:21:00Z","title":"Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10508","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:c18f1213dbd78a6c7e8cf75272fc5e37738426a0caf6d168ffc247cafc567631","target":"record","created_at":"2026-07-05T10:17:05Z","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":"5ee756fda3e4b4cdabfea7aebeaa6c38587ab53421666634461f31747f03b5d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-10-11T00:21:00Z","title_canon_sha256":"f01f4cfbae37a2b15c272b677fa48977827319954128e8351f5944081395f21f"},"schema_version":"1.0","source":{"id":"2310.10508","kind":"arxiv","version":2}},"canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","first_computed_at":"2026-07-05T10:17:05.474449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:05.474449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DgovR6mR/rBisoY7V39amPi4Jmx1oSfi9g7Xp/1GqUUF53YbtTB11stCW+Bv18p/xYURHP8t7/qq8gezq18rDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:05.474939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c18f1213dbd78a6c7e8cf75272fc5e37738426a0caf6d168ffc247cafc567631","sha256:0c49d03a1f426720b63304a06537fb1cb63b1894b984ea9985295e29f14d02f8"],"state_sha256":"21909df15794bbe88d424a82f8a3bd6f46869de56e4a7dc9bda66e476bc410e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qemIsFlIMY1g6Bb0/XXUnfx5UFn3jahsMuum8kt4h8nlyHBdva80eLd2oDuPenzhD7vTRf7VJ8ZnDJpqrZ1eBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:26:14.915976Z","bundle_sha256":"3480c6f55a02ca4d5608df03777c4fbc89523846ea182f04e19461f4acfb4210"}}