{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2QAR4YWFPB5B3ZXPFYWED4II2A","short_pith_number":"pith:2QAR4YWF","canonical_record":{"source":{"id":"2304.05216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-04-11T13:34:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6c10f322c692c2b6dbb2aba70a0f4e1ace410507109aad5f84894915f64dd43c","abstract_canon_sha256":"2b44a97b32209e906cc592cd85303e328f43c9c37b7c583b4ef87f36e8cc6256"},"schema_version":"1.0"},"canonical_sha256":"d4011e62c5787a1de6ef2e2c41f108d02203e343555d556f0e0fb53bdf60856d","source":{"kind":"arxiv","id":"2304.05216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05216","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05216v1","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05216","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"2QAR4YWFPB5B","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"2QAR4YWFPB5B3ZXP","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"2QAR4YWF","created_at":"2026-07-05T05:59:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2QAR4YWFPB5B3ZXPFYWED4II2A","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-04-11T13:34:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6c10f322c692c2b6dbb2aba70a0f4e1ace410507109aad5f84894915f64dd43c","abstract_canon_sha256":"2b44a97b32209e906cc592cd85303e328f43c9c37b7c583b4ef87f36e8cc6256"},"schema_version":"1.0"},"canonical_sha256":"d4011e62c5787a1de6ef2e2c41f108d02203e343555d556f0e0fb53bdf60856d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:57.302134Z","signature_b64":"F5WVLyg+1ZAoQMxuw58TiRpkgb3OaeCwo3hGbtKk0nB1vHyNtVb1RWOcTY8eYcisLL8FSerjRQxpLfUhfwMUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4011e62c5787a1de6ef2e2c41f108d02203e343555d556f0e0fb53bdf60856d","last_reissued_at":"2026-07-05T05:59:57.301738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:57.301738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05216","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":"2026-07-05T05:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbwlYbv2+NgOCHLT0kCwMzC7GB0TlS30LloAzqQuzpMS9IhwGn4weCuF4jqLeXiDo/th25ZgH0VT/026FpTBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:04:23.932769Z"},"content_sha256":"732bcbde419da29901a3fd7413fff660efed00288901594be06ae18a6f323886","schema_version":"1.0","event_id":"sha256:732bcbde419da29901a3fd7413fff660efed00288901594be06ae18a6f323886"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2QAR4YWFPB5B3ZXPFYWED4II2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dongmei Zhang, Ensheng Shi, Hongbin Sun, Hongyu Zhang, Lun Du, Shi Han, Yanlin Wang","submitted_at":"2023-04-11T13:34:13Z","abstract_excerpt":"Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large computational cost. In this paper, we conduct an extensive experimental study to explore what happens to layer-wise pre-trained representations and their encoded code knowledge during fine-tuning. We then propose efficient alternatives to fine-tune the large pre-trained code model based on the above findings. Our experimental study shows that (1) lexical, sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05216","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/2304.05216/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":"2026-07-05T05:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obomWJT8J1wSPmAbVNSw0DvGcJMm5KMuth/N7lTKL5CF6m/O17eaKZPRmvh1eJMdV8pjoA4FwHTkm5fgf4woCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:04:23.933148Z"},"content_sha256":"25c4d59cc01b040a3c1feaf89f10124801c563c6025867c9a898556844fc6939","schema_version":"1.0","event_id":"sha256:25c4d59cc01b040a3c1feaf89f10124801c563c6025867c9a898556844fc6939"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QAR4YWFPB5B3ZXPFYWED4II2A/bundle.json","state_url":"https://pith.science/pith/2QAR4YWFPB5B3ZXPFYWED4II2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QAR4YWFPB5B3ZXPFYWED4II2A/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":"2026-07-07T05:04:23Z","links":{"resolver":"https://pith.science/pith/2QAR4YWFPB5B3ZXPFYWED4II2A","bundle":"https://pith.science/pith/2QAR4YWFPB5B3ZXPFYWED4II2A/bundle.json","state":"https://pith.science/pith/2QAR4YWFPB5B3ZXPFYWED4II2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QAR4YWFPB5B3ZXPFYWED4II2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2QAR4YWFPB5B3ZXPFYWED4II2A","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":"2b44a97b32209e906cc592cd85303e328f43c9c37b7c583b4ef87f36e8cc6256","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-04-11T13:34:13Z","title_canon_sha256":"6c10f322c692c2b6dbb2aba70a0f4e1ace410507109aad5f84894915f64dd43c"},"schema_version":"1.0","source":{"id":"2304.05216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05216","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05216v1","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05216","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"2QAR4YWFPB5B","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"2QAR4YWFPB5B3ZXP","created_at":"2026-07-05T05:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"2QAR4YWF","created_at":"2026-07-05T05:59:57Z"}],"graph_snapshots":[{"event_id":"sha256:25c4d59cc01b040a3c1feaf89f10124801c563c6025867c9a898556844fc6939","target":"graph","created_at":"2026-07-05T05:59:57Z","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/2304.05216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large computational cost. In this paper, we conduct an extensive experimental study to explore what happens to layer-wise pre-trained representations and their encoded code knowledge during fine-tuning. We then propose efficient alternatives to fine-tune the large pre-trained code model based on the above findings. Our experimental study shows that (1) lexical, sy","authors_text":"Dongmei Zhang, Ensheng Shi, Hongbin Sun, Hongyu Zhang, Lun Du, Shi Han, Yanlin Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-04-11T13:34:13Z","title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05216","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":"sha256:732bcbde419da29901a3fd7413fff660efed00288901594be06ae18a6f323886","target":"record","created_at":"2026-07-05T05:59:57Z","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":"2b44a97b32209e906cc592cd85303e328f43c9c37b7c583b4ef87f36e8cc6256","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-04-11T13:34:13Z","title_canon_sha256":"6c10f322c692c2b6dbb2aba70a0f4e1ace410507109aad5f84894915f64dd43c"},"schema_version":"1.0","source":{"id":"2304.05216","kind":"arxiv","version":1}},"canonical_sha256":"d4011e62c5787a1de6ef2e2c41f108d02203e343555d556f0e0fb53bdf60856d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4011e62c5787a1de6ef2e2c41f108d02203e343555d556f0e0fb53bdf60856d","first_computed_at":"2026-07-05T05:59:57.301738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:57.301738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F5WVLyg+1ZAoQMxuw58TiRpkgb3OaeCwo3hGbtKk0nB1vHyNtVb1RWOcTY8eYcisLL8FSerjRQxpLfUhfwMUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:57.302134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:732bcbde419da29901a3fd7413fff660efed00288901594be06ae18a6f323886","sha256:25c4d59cc01b040a3c1feaf89f10124801c563c6025867c9a898556844fc6939"],"state_sha256":"d3d5ef6146637138282c35a6e2554caeaf6b070709efc6471046940713a319ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"txsaPI7KjJEseXwlEYRMPnqPNAegoSnhYlABA1BMh19lBk02lkehr5nw3P0w+le9h1/eN6Eikt2iFFfUEZUzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:04:23.935276Z","bundle_sha256":"15a1dd4b5f61055b18e7976c4c459fb4bfef7ee8b3a11b98fc5641d51eb36640"}}