{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XGPQL4YTB7YUVP37RVUAKEU6ZE","short_pith_number":"pith:XGPQL4YT","canonical_record":{"source":{"id":"2505.18789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-24T17:06:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c9b52b20c1b8a6570c444e1aae017ebc11a86d40d7003375f51c3f500ce2218a","abstract_canon_sha256":"f3c978238193184c6f921f3790f7159cdb2135c6fd929fb2cbb3a15b568bd01e"},"schema_version":"1.0"},"canonical_sha256":"b99f05f3130ff14abf7f8d6805129ec91dbe3c4eb1921db59f511ad31522d847","source":{"kind":"arxiv","id":"2505.18789","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18789","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18789v2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18789","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"XGPQL4YTB7YU","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"XGPQL4YTB7YUVP37","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"XGPQL4YT","created_at":"2026-07-05T11:18:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XGPQL4YTB7YUVP37RVUAKEU6ZE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-24T17:06:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c9b52b20c1b8a6570c444e1aae017ebc11a86d40d7003375f51c3f500ce2218a","abstract_canon_sha256":"f3c978238193184c6f921f3790f7159cdb2135c6fd929fb2cbb3a15b568bd01e"},"schema_version":"1.0"},"canonical_sha256":"b99f05f3130ff14abf7f8d6805129ec91dbe3c4eb1921db59f511ad31522d847","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:43.142447Z","signature_b64":"nOv9KMIXbAfzVvaCwc1o1U3yqFZ3wglxP7rAXAgHILdKQKEPcg8d0SkbXVZChpu56ffx4Hx4cfFPS2cNy086CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b99f05f3130ff14abf7f8d6805129ec91dbe3c4eb1921db59f511ad31522d847","last_reissued_at":"2026-07-05T11:18:43.141971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:43.141971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18789","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":"2026-07-05T11:18:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCM5uix2vKtU203m5rBger81LXbVRzJxZJuIt6pnOd2HPPSc4BiKhk3frR6hT4siC4/CEslu1ypXiAaQNmngBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:09:43.429493Z"},"content_sha256":"f6f1dacec486bceb966ecf45dd41805bbeb5f63433ff7380bc6c9ea194531100","schema_version":"1.0","event_id":"sha256:f6f1dacec486bceb966ecf45dd41805bbeb5f63433ff7380bc6c9ea194531100"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XGPQL4YTB7YUVP37RVUAKEU6ZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Boris Ginsburg, Somshubra Majumdar, Wasi Uddin Ahmad","submitted_at":"2025-05-24T17:06:47Z","abstract_excerpt":"Post-processing is crucial for the automatic evaluation of LLMs in fill-in-the-middle (FIM) code generation due to the frequent presence of extraneous code in raw outputs. This extraneous generation suggests a lack of awareness regarding output boundaries, requiring truncation for effective evaluation. The determination of an optimal truncation strategy, however, often proves intricate, particularly when the scope includes several programming languages. This study investigates the necessity of post-processing instruction-tuned LLM outputs. Our findings reveal that supervised fine-tuning signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18789","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/2505.18789/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":"2026-07-05T11:18:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zinRV2AV3gZt/dbRLlusVzXaBCogvT67yCTt53jo3Uvnee7dMGY/UnzrhQA5UE/vIaa/rkJJKufRlM54WX/ICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:09:43.429868Z"},"content_sha256":"7888d57a231ca7d91d62035d0685346a4af8657d9e33f5dd861eb6450c1ce002","schema_version":"1.0","event_id":"sha256:7888d57a231ca7d91d62035d0685346a4af8657d9e33f5dd861eb6450c1ce002"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE/bundle.json","state_url":"https://pith.science/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE/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":"2026-07-06T09:09:43Z","links":{"resolver":"https://pith.science/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE","bundle":"https://pith.science/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE/bundle.json","state":"https://pith.science/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGPQL4YTB7YUVP37RVUAKEU6ZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XGPQL4YTB7YUVP37RVUAKEU6ZE","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":"f3c978238193184c6f921f3790f7159cdb2135c6fd929fb2cbb3a15b568bd01e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-24T17:06:47Z","title_canon_sha256":"c9b52b20c1b8a6570c444e1aae017ebc11a86d40d7003375f51c3f500ce2218a"},"schema_version":"1.0","source":{"id":"2505.18789","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18789","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18789v2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18789","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"XGPQL4YTB7YU","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"XGPQL4YTB7YUVP37","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"XGPQL4YT","created_at":"2026-07-05T11:18:43Z"}],"graph_snapshots":[{"event_id":"sha256:7888d57a231ca7d91d62035d0685346a4af8657d9e33f5dd861eb6450c1ce002","target":"graph","created_at":"2026-07-05T11:18:43Z","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/2505.18789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-processing is crucial for the automatic evaluation of LLMs in fill-in-the-middle (FIM) code generation due to the frequent presence of extraneous code in raw outputs. This extraneous generation suggests a lack of awareness regarding output boundaries, requiring truncation for effective evaluation. The determination of an optimal truncation strategy, however, often proves intricate, particularly when the scope includes several programming languages. This study investigates the necessity of post-processing instruction-tuned LLM outputs. Our findings reveal that supervised fine-tuning signif","authors_text":"Boris Ginsburg, Somshubra Majumdar, Wasi Uddin Ahmad","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-24T17:06:47Z","title":"From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18789","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:f6f1dacec486bceb966ecf45dd41805bbeb5f63433ff7380bc6c9ea194531100","target":"record","created_at":"2026-07-05T11:18:43Z","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":"f3c978238193184c6f921f3790f7159cdb2135c6fd929fb2cbb3a15b568bd01e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-24T17:06:47Z","title_canon_sha256":"c9b52b20c1b8a6570c444e1aae017ebc11a86d40d7003375f51c3f500ce2218a"},"schema_version":"1.0","source":{"id":"2505.18789","kind":"arxiv","version":2}},"canonical_sha256":"b99f05f3130ff14abf7f8d6805129ec91dbe3c4eb1921db59f511ad31522d847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b99f05f3130ff14abf7f8d6805129ec91dbe3c4eb1921db59f511ad31522d847","first_computed_at":"2026-07-05T11:18:43.141971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:43.141971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nOv9KMIXbAfzVvaCwc1o1U3yqFZ3wglxP7rAXAgHILdKQKEPcg8d0SkbXVZChpu56ffx4Hx4cfFPS2cNy086CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:43.142447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18789","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6f1dacec486bceb966ecf45dd41805bbeb5f63433ff7380bc6c9ea194531100","sha256:7888d57a231ca7d91d62035d0685346a4af8657d9e33f5dd861eb6450c1ce002"],"state_sha256":"96943a1d0ddc78e2c65b6429e8b7db911a82dee45edc20c6f3bae936712659e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HP0OXjto7LBYRxe2jTqnStQPxN3hlImqhut2qZgiGoTFSclygu9jamUGIUpv1jfBiDvpZe2N7v6FVCnqLwPUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:09:43.431771Z","bundle_sha256":"d3a2855525374ad574a865525cbaa96e5789f4d45e116ddc3a26b351b47f640e"}}