{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GP4XIAVNBMALXSTTRQISPNSDCG","short_pith_number":"pith:GP4XIAVN","canonical_record":{"source":{"id":"2411.14971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T14:27:27Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"1412b91b62864586d5394babf774056333a75b5450f4a8e7feb23cdd98b119d9","abstract_canon_sha256":"8a6e97ee61c7d2391b77c4f07fbc29f18441f7c024e9b5474eb1a2cd101f3e5c"},"schema_version":"1.0"},"canonical_sha256":"33f97402ad0b00bbca738c1127b64311adc57d2200cbbbd6f90d505d57394e9f","source":{"kind":"arxiv","id":"2411.14971","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14971","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14971v1","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14971","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"pith_short_12","alias_value":"GP4XIAVNBMAL","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"pith_short_16","alias_value":"GP4XIAVNBMALXSTT","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"pith_short_8","alias_value":"GP4XIAVN","created_at":"2026-07-05T09:39:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GP4XIAVNBMALXSTTRQISPNSDCG","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T14:27:27Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"1412b91b62864586d5394babf774056333a75b5450f4a8e7feb23cdd98b119d9","abstract_canon_sha256":"8a6e97ee61c7d2391b77c4f07fbc29f18441f7c024e9b5474eb1a2cd101f3e5c"},"schema_version":"1.0"},"canonical_sha256":"33f97402ad0b00bbca738c1127b64311adc57d2200cbbbd6f90d505d57394e9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:14.388808Z","signature_b64":"gD+oLtKF2HpnsidH0zuGaulMO+GYb+AQh5YFz3JNkSKztxBa/1DTCktkAwIzH7fRn2pwzqjq62CvpPT5wB0nCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f97402ad0b00bbca738c1127b64311adc57d2200cbbbd6f90d505d57394e9f","last_reissued_at":"2026-07-05T09:39:14.388394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:14.388394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14971","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":"2026-07-05T09:39:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKW9iJEla+y3sY3pkGWF99X4s6IY6uaE7z0yPs9ag01c2Vq8SkVQQkNjlW3VGeN0K5ZQRrpTtxyKAhZl4xNqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:25:07.827772Z"},"content_sha256":"eb3159e8a64bb054e4a0e96b3db373cdac6cc3bba046af1118a9721b009f66d0","schema_version":"1.0","event_id":"sha256:eb3159e8a64bb054e4a0e96b3db373cdac6cc3bba046af1118a9721b009f66d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GP4XIAVNBMALXSTTRQISPNSDCG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Amit Madan, Anand Patel, Arun Sridharan, Chris Glasz, Colin Diggs, Doug Wendt, Emily Escamilla, Jacob Zimmer, Jasper Phillips, Justin F. Brunelle, Michael Bartholf, Michael Doyle, Naveed Nekoo, Nitin Naik, Paul Kirk, Paul Ursino, Samruddhi Thaker, Scott Rosen, Siggy Scott, William Macke, Zachary Robin","submitted_at":"2024-11-22T14:27:27Z","abstract_excerpt":"Legacy software systems, written in outdated languages like MUMPS and mainframe assembly, pose challenges in efficiency, maintenance, staffing, and security. While LLMs offer promise for modernizing these systems, their ability to understand legacy languages is largely unknown. This paper investigates the utilization of LLMs to generate documentation for legacy code using two datasets: an electronic health records (EHR) system in MUMPS and open-source applications in IBM mainframe Assembly Language Code (ALC). We propose a prompting strategy for generating line-wise code comments and a rubric "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14971","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/2411.14971/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":"2026-07-05T09:39:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OK4IIlNQEPSgJQJjS3a0XFA3rv3w+Pj6UzEYCgrg9+tNyUv1IR0l1afL0F/gs3BwZsKNgAFHr2cf063Hg9hgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:25:07.828154Z"},"content_sha256":"c55b8196ed7133a1492f5cb4c547ae7e559fcd1f01b31ec1f5f25d928b2c0c92","schema_version":"1.0","event_id":"sha256:c55b8196ed7133a1492f5cb4c547ae7e559fcd1f01b31ec1f5f25d928b2c0c92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GP4XIAVNBMALXSTTRQISPNSDCG/bundle.json","state_url":"https://pith.science/pith/GP4XIAVNBMALXSTTRQISPNSDCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GP4XIAVNBMALXSTTRQISPNSDCG/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":"2026-07-06T17:25:07Z","links":{"resolver":"https://pith.science/pith/GP4XIAVNBMALXSTTRQISPNSDCG","bundle":"https://pith.science/pith/GP4XIAVNBMALXSTTRQISPNSDCG/bundle.json","state":"https://pith.science/pith/GP4XIAVNBMALXSTTRQISPNSDCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GP4XIAVNBMALXSTTRQISPNSDCG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GP4XIAVNBMALXSTTRQISPNSDCG","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":"8a6e97ee61c7d2391b77c4f07fbc29f18441f7c024e9b5474eb1a2cd101f3e5c","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T14:27:27Z","title_canon_sha256":"1412b91b62864586d5394babf774056333a75b5450f4a8e7feb23cdd98b119d9"},"schema_version":"1.0","source":{"id":"2411.14971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14971","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14971v1","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14971","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"pith_short_12","alias_value":"GP4XIAVNBMAL","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"pith_short_16","alias_value":"GP4XIAVNBMALXSTT","created_at":"2026-07-05T09:39:14Z"},{"alias_kind":"pith_short_8","alias_value":"GP4XIAVN","created_at":"2026-07-05T09:39:14Z"}],"graph_snapshots":[{"event_id":"sha256:c55b8196ed7133a1492f5cb4c547ae7e559fcd1f01b31ec1f5f25d928b2c0c92","target":"graph","created_at":"2026-07-05T09:39:14Z","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/2411.14971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Legacy software systems, written in outdated languages like MUMPS and mainframe assembly, pose challenges in efficiency, maintenance, staffing, and security. While LLMs offer promise for modernizing these systems, their ability to understand legacy languages is largely unknown. This paper investigates the utilization of LLMs to generate documentation for legacy code using two datasets: an electronic health records (EHR) system in MUMPS and open-source applications in IBM mainframe Assembly Language Code (ALC). We propose a prompting strategy for generating line-wise code comments and a rubric ","authors_text":"Amit Madan, Anand Patel, Arun Sridharan, Chris Glasz, Colin Diggs, Doug Wendt, Emily Escamilla, Jacob Zimmer, Jasper Phillips, Justin F. Brunelle, Michael Bartholf, Michael Doyle, Naveed Nekoo, Nitin Naik, Paul Kirk, Paul Ursino, Samruddhi Thaker, Scott Rosen, Siggy Scott, William Macke, Zachary Robin","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T14:27:27Z","title":"Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14971","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:eb3159e8a64bb054e4a0e96b3db373cdac6cc3bba046af1118a9721b009f66d0","target":"record","created_at":"2026-07-05T09:39:14Z","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":"8a6e97ee61c7d2391b77c4f07fbc29f18441f7c024e9b5474eb1a2cd101f3e5c","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T14:27:27Z","title_canon_sha256":"1412b91b62864586d5394babf774056333a75b5450f4a8e7feb23cdd98b119d9"},"schema_version":"1.0","source":{"id":"2411.14971","kind":"arxiv","version":1}},"canonical_sha256":"33f97402ad0b00bbca738c1127b64311adc57d2200cbbbd6f90d505d57394e9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33f97402ad0b00bbca738c1127b64311adc57d2200cbbbd6f90d505d57394e9f","first_computed_at":"2026-07-05T09:39:14.388394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:14.388394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gD+oLtKF2HpnsidH0zuGaulMO+GYb+AQh5YFz3JNkSKztxBa/1DTCktkAwIzH7fRn2pwzqjq62CvpPT5wB0nCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:14.388808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb3159e8a64bb054e4a0e96b3db373cdac6cc3bba046af1118a9721b009f66d0","sha256:c55b8196ed7133a1492f5cb4c547ae7e559fcd1f01b31ec1f5f25d928b2c0c92"],"state_sha256":"3bd6c59af7332ea07e65020380a75308cf63689885b0b5b0a642064e323094d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8zkxSTzFw3nlVPhIWIq9Sf2SurAPdYQpweYgBIqwvX+DzDxFN4T9fSOC3zt3O93JJyqcD6HYAX60AMTBDssDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:25:07.830684Z","bundle_sha256":"2659f66c9d792c60d8379e743f1c3cc8a8df4dcc6f8038562ef5d207fc4bf583"}}