{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G43CFVZW7YGK6D6FNO3RROHA53","short_pith_number":"pith:G43CFVZW","canonical_record":{"source":{"id":"2110.05423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"b9c5e649c84cbe0636bf65263bbdd6a4bb12f4a5fbedaa45a46468913736c3f7","abstract_canon_sha256":"a6658d35dc2551f13ddbec076f1930c625d4c7ca59fe388498ff7036a262b029"},"schema_version":"1.0"},"canonical_sha256":"373622d736fe0caf0fc56bb718b8e0eec5c53d445bd9ae1e0bcee486e821e4c7","source":{"kind":"arxiv","id":"2110.05423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05423","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05423v1","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05423","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"G43CFVZW7YGK","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"pith_short_16","alias_value":"G43CFVZW7YGK6D6F","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"pith_short_8","alias_value":"G43CFVZW","created_at":"2026-07-05T03:21:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G43CFVZW7YGK6D6FNO3RROHA53","target":"record","payload":{"canonical_record":{"source":{"id":"2110.05423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"b9c5e649c84cbe0636bf65263bbdd6a4bb12f4a5fbedaa45a46468913736c3f7","abstract_canon_sha256":"a6658d35dc2551f13ddbec076f1930c625d4c7ca59fe388498ff7036a262b029"},"schema_version":"1.0"},"canonical_sha256":"373622d736fe0caf0fc56bb718b8e0eec5c53d445bd9ae1e0bcee486e821e4c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:34.845962Z","signature_b64":"ZGmHU3N8+fRnMcrPUJ74fIQ2QsiDwnHs20+nWy3+LpAAU9mdaN6iKsCoDPB1vlxmOLyndZzL5E2MkSbMzJAcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"373622d736fe0caf0fc56bb718b8e0eec5c53d445bd9ae1e0bcee486e821e4c7","last_reissued_at":"2026-07-05T03:21:34.845564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:34.845564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.05423","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":"2026-07-05T03:21:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bx2NM+/MmlAsvX5iZja9IdA/NTvs8Ks/6mVHmPEvGNpkST5S2I4SOrTF+WWk2oOaW2Fgl0eN4LOPVBJQ1i8kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:12:56.852521Z"},"content_sha256":"84e4a754fb29130a881fba0b00f156ebefa07eae654a76b1bbb11a3b7e9c8a5d","schema_version":"1.0","event_id":"sha256:84e4a754fb29130a881fba0b00f156ebefa07eae654a76b1bbb11a3b7e9c8a5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G43CFVZW7YGK6D6FNO3RROHA53","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Document Similarity Methods to create Parallel Datasets for Code Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fernando Martinez, John Richards, Justin D. Weisz, Kartik Talamadupula, Mayank Agarwal, Michael Muller, Stephanie Houde, Steven I Ross","submitted_at":"2021-10-11T17:07:58Z","abstract_excerpt":"Translating source code from one programming language to another is a critical, time-consuming task in modernizing legacy applications and codebases. Recent work in this space has drawn inspiration from the software naturalness hypothesis by applying natural language processing techniques towards automating the code translation task. However, due to the paucity of parallel data in this domain, supervised techniques have only been applied to a limited set of popular programming languages. To bypass this limitation, unsupervised neural machine translation techniques have been proposed to learn c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05423","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/2110.05423/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":"2026-07-05T03:21:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NRA5KAMTL4nPin+2ZRGIy5fm97hySqWNSyi0pmd1yCLUk3ThMhPTUqbxG+JN2POWJD69jRT117Z0FesJPnjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:12:56.852892Z"},"content_sha256":"10260d36a814569d63c12a9beae48736ca484047ab0269d01307a3b11c932e18","schema_version":"1.0","event_id":"sha256:10260d36a814569d63c12a9beae48736ca484047ab0269d01307a3b11c932e18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G43CFVZW7YGK6D6FNO3RROHA53/bundle.json","state_url":"https://pith.science/pith/G43CFVZW7YGK6D6FNO3RROHA53/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G43CFVZW7YGK6D6FNO3RROHA53/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":"2026-07-06T18:12:56Z","links":{"resolver":"https://pith.science/pith/G43CFVZW7YGK6D6FNO3RROHA53","bundle":"https://pith.science/pith/G43CFVZW7YGK6D6FNO3RROHA53/bundle.json","state":"https://pith.science/pith/G43CFVZW7YGK6D6FNO3RROHA53/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G43CFVZW7YGK6D6FNO3RROHA53/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G43CFVZW7YGK6D6FNO3RROHA53","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":"a6658d35dc2551f13ddbec076f1930c625d4c7ca59fe388498ff7036a262b029","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:07:58Z","title_canon_sha256":"b9c5e649c84cbe0636bf65263bbdd6a4bb12f4a5fbedaa45a46468913736c3f7"},"schema_version":"1.0","source":{"id":"2110.05423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05423","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05423v1","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05423","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"G43CFVZW7YGK","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"pith_short_16","alias_value":"G43CFVZW7YGK6D6F","created_at":"2026-07-05T03:21:34Z"},{"alias_kind":"pith_short_8","alias_value":"G43CFVZW","created_at":"2026-07-05T03:21:34Z"}],"graph_snapshots":[{"event_id":"sha256:10260d36a814569d63c12a9beae48736ca484047ab0269d01307a3b11c932e18","target":"graph","created_at":"2026-07-05T03:21:34Z","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/2110.05423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Translating source code from one programming language to another is a critical, time-consuming task in modernizing legacy applications and codebases. Recent work in this space has drawn inspiration from the software naturalness hypothesis by applying natural language processing techniques towards automating the code translation task. However, due to the paucity of parallel data in this domain, supervised techniques have only been applied to a limited set of popular programming languages. To bypass this limitation, unsupervised neural machine translation techniques have been proposed to learn c","authors_text":"Fernando Martinez, John Richards, Justin D. Weisz, Kartik Talamadupula, Mayank Agarwal, Michael Muller, Stephanie Houde, Steven I Ross","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:07:58Z","title":"Using Document Similarity Methods to create Parallel Datasets for Code Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05423","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":"sha256:84e4a754fb29130a881fba0b00f156ebefa07eae654a76b1bbb11a3b7e9c8a5d","target":"record","created_at":"2026-07-05T03:21:34Z","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":"a6658d35dc2551f13ddbec076f1930c625d4c7ca59fe388498ff7036a262b029","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:07:58Z","title_canon_sha256":"b9c5e649c84cbe0636bf65263bbdd6a4bb12f4a5fbedaa45a46468913736c3f7"},"schema_version":"1.0","source":{"id":"2110.05423","kind":"arxiv","version":1}},"canonical_sha256":"373622d736fe0caf0fc56bb718b8e0eec5c53d445bd9ae1e0bcee486e821e4c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"373622d736fe0caf0fc56bb718b8e0eec5c53d445bd9ae1e0bcee486e821e4c7","first_computed_at":"2026-07-05T03:21:34.845564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:34.845564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZGmHU3N8+fRnMcrPUJ74fIQ2QsiDwnHs20+nWy3+LpAAU9mdaN6iKsCoDPB1vlxmOLyndZzL5E2MkSbMzJAcAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:34.845962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e4a754fb29130a881fba0b00f156ebefa07eae654a76b1bbb11a3b7e9c8a5d","sha256:10260d36a814569d63c12a9beae48736ca484047ab0269d01307a3b11c932e18"],"state_sha256":"52b070da4f3e29c3b3c7859ba04099ec7883527e9bfd8f38a0e29fee0ebcfa8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HLMt7IgQxkWMDkf4JyjWEKc/L5U+8dE2MG4+CG3X7L9zLDPrLbcLv0diNG5W6di4eTnis4qT0lYaniH65/fxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:12:56.854863Z","bundle_sha256":"870f902ea4a48f14607b224917407669472bf0a68c693038e24af480d7efa727"}}