{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C7MUMNJG3KW7KLTTXUAFAKIKKH","short_pith_number":"pith:C7MUMNJG","canonical_record":{"source":{"id":"2507.22066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-02T15:15:12Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"f0e53e4e3d0df4c4331dc615a3df62a07dd98a9ff9d277315da77f58fa42fb2d","abstract_canon_sha256":"95a1f976273d07b11bbbd9b453366d98045f43d1996998a35032477c0acaa912"},"schema_version":"1.0"},"canonical_sha256":"17d9463526daadf52e73bd0050290a51dbbdbad6520d131c23b6ee13238e7ff6","source":{"kind":"arxiv","id":"2507.22066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22066","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22066v1","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22066","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"pith_short_12","alias_value":"C7MUMNJG3KW7","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"pith_short_16","alias_value":"C7MUMNJG3KW7KLTT","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"pith_short_8","alias_value":"C7MUMNJG","created_at":"2026-07-05T11:45:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C7MUMNJG3KW7KLTTXUAFAKIKKH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-02T15:15:12Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"f0e53e4e3d0df4c4331dc615a3df62a07dd98a9ff9d277315da77f58fa42fb2d","abstract_canon_sha256":"95a1f976273d07b11bbbd9b453366d98045f43d1996998a35032477c0acaa912"},"schema_version":"1.0"},"canonical_sha256":"17d9463526daadf52e73bd0050290a51dbbdbad6520d131c23b6ee13238e7ff6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:15.769210Z","signature_b64":"bwdl3sfiCvzFTXGlT0vUV8Y4oBVgHTdDSMqixfP1SY9SluiUgL5tsXzbz4igsC/7B7vDT16M5J1KwyUinxHDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17d9463526daadf52e73bd0050290a51dbbdbad6520d131c23b6ee13238e7ff6","last_reissued_at":"2026-07-05T11:45:15.768780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:15.768780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22066","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":"2026-07-05T11:45:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIPxTnVfxkHCF1c96hdXN556mQg9DwvLAQptoyE2fZ8tmI+8E4Ldb/BRktfN986G4aGw7Ukp9F/Avg2IWv1FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:48:36.124920Z"},"content_sha256":"ea40bf74b0fc038099f3857759ec480b79e9cd1cf26d57fb973d7a77299a2e6d","schema_version":"1.0","event_id":"sha256:ea40bf74b0fc038099f3857759ec480b79e9cd1cf26d57fb973d7a77299a2e6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C7MUMNJG3KW7KLTTXUAFAKIKKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodableLLM: Automating Decompiled and Source Code Mapping for LLM Dataset Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Dylan Manuel, Paul Rad","submitted_at":"2025-07-02T15:15:12Z","abstract_excerpt":"The generation of large, high-quality datasets for code understanding and generation remains a significant challenge, particularly when aligning decompiled binaries with their original source code. To address this, we present CodableLLM, a Python framework designed to automate the creation and curation of datasets by mapping decompiled functions to their corresponding source functions. This process enhances the alignment between decompiled and source code representations, facilitating the development of large language models (LLMs) capable of understanding and generating code across multiple a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22066","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/2507.22066/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":"2026-07-05T11:45:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRyxA7TAQsVb40bN+8mT3rGzAaG05i4b2nSlJYxJIHx3AT+EZwsxwwUE7l/x88yJxwla0x1nAHFDLeXaBdHFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:48:36.125887Z"},"content_sha256":"7c80ff7173b0cb316a0865cda49271e2f4fa3582fda75e3fba2998aab6800849","schema_version":"1.0","event_id":"sha256:7c80ff7173b0cb316a0865cda49271e2f4fa3582fda75e3fba2998aab6800849"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH/bundle.json","state_url":"https://pith.science/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH/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":"2026-08-17T21:48:36Z","links":{"resolver":"https://pith.science/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH","bundle":"https://pith.science/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH/bundle.json","state":"https://pith.science/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C7MUMNJG3KW7KLTTXUAFAKIKKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C7MUMNJG3KW7KLTTXUAFAKIKKH","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":"95a1f976273d07b11bbbd9b453366d98045f43d1996998a35032477c0acaa912","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-02T15:15:12Z","title_canon_sha256":"f0e53e4e3d0df4c4331dc615a3df62a07dd98a9ff9d277315da77f58fa42fb2d"},"schema_version":"1.0","source":{"id":"2507.22066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22066","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22066v1","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22066","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"pith_short_12","alias_value":"C7MUMNJG3KW7","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"pith_short_16","alias_value":"C7MUMNJG3KW7KLTT","created_at":"2026-07-05T11:45:15Z"},{"alias_kind":"pith_short_8","alias_value":"C7MUMNJG","created_at":"2026-07-05T11:45:15Z"}],"graph_snapshots":[{"event_id":"sha256:7c80ff7173b0cb316a0865cda49271e2f4fa3582fda75e3fba2998aab6800849","target":"graph","created_at":"2026-07-05T11:45:15Z","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/2507.22066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The generation of large, high-quality datasets for code understanding and generation remains a significant challenge, particularly when aligning decompiled binaries with their original source code. To address this, we present CodableLLM, a Python framework designed to automate the creation and curation of datasets by mapping decompiled functions to their corresponding source functions. This process enhances the alignment between decompiled and source code representations, facilitating the development of large language models (LLMs) capable of understanding and generating code across multiple a","authors_text":"Dylan Manuel, Paul Rad","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-02T15:15:12Z","title":"CodableLLM: Automating Decompiled and Source Code Mapping for LLM Dataset Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22066","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:ea40bf74b0fc038099f3857759ec480b79e9cd1cf26d57fb973d7a77299a2e6d","target":"record","created_at":"2026-07-05T11:45:15Z","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":"95a1f976273d07b11bbbd9b453366d98045f43d1996998a35032477c0acaa912","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-02T15:15:12Z","title_canon_sha256":"f0e53e4e3d0df4c4331dc615a3df62a07dd98a9ff9d277315da77f58fa42fb2d"},"schema_version":"1.0","source":{"id":"2507.22066","kind":"arxiv","version":1}},"canonical_sha256":"17d9463526daadf52e73bd0050290a51dbbdbad6520d131c23b6ee13238e7ff6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17d9463526daadf52e73bd0050290a51dbbdbad6520d131c23b6ee13238e7ff6","first_computed_at":"2026-07-05T11:45:15.768780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:15.768780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bwdl3sfiCvzFTXGlT0vUV8Y4oBVgHTdDSMqixfP1SY9SluiUgL5tsXzbz4igsC/7B7vDT16M5J1KwyUinxHDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:15.769210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea40bf74b0fc038099f3857759ec480b79e9cd1cf26d57fb973d7a77299a2e6d","sha256:7c80ff7173b0cb316a0865cda49271e2f4fa3582fda75e3fba2998aab6800849"],"state_sha256":"092769278240aa01ef7769e9e7eec35aa9086d84ae47fba4a5918dbc595260df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bebJ/D+ElJ+ZsN51XKX346Tpe2DzfIZe9yo2s1kbzP+dkfa+BNo5VQeSEecJKnnE4lUbhn/nrYSd2XQnJNWvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:48:36.131485Z","bundle_sha256":"d61696972797fe5073909e7d26d0a276db8ae01574737ceadc7b036dff18dda8"}}