{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2NEKVEI2CWOROWUZZVBCCGIMBX","short_pith_number":"pith:2NEKVEI2","canonical_record":{"source":{"id":"1904.11968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-26T17:52:06Z","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"title_canon_sha256":"7b3c096edcae673e9a55f553ed92644f4d11810ef2d986e65f62e2b7f95ea562","abstract_canon_sha256":"38d64fe52b74943d2d147cdd00b222e709131fc1be47514e0e3c8056776a1965"},"schema_version":"1.0"},"canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","source":{"kind":"arxiv","id":"1904.11968","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11968","created_at":"2026-05-17T23:47:40Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11968v1","created_at":"2026-05-17T23:47:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11968","created_at":"2026-05-17T23:47:40Z"},{"alias_kind":"pith_short_12","alias_value":"2NEKVEI2CWOR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2NEKVEI2CWOROWUZ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2NEKVEI2","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2NEKVEI2CWOROWUZZVBCCGIMBX","target":"record","payload":{"canonical_record":{"source":{"id":"1904.11968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-26T17:52:06Z","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"title_canon_sha256":"7b3c096edcae673e9a55f553ed92644f4d11810ef2d986e65f62e2b7f95ea562","abstract_canon_sha256":"38d64fe52b74943d2d147cdd00b222e709131fc1be47514e0e3c8056776a1965"},"schema_version":"1.0"},"canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:40.501155Z","signature_b64":"Gw8ynr1aYrWz9Etwk5AKycm7WK7gSkg7gYg6nuFpr7dEF6s6fD5mvTWdypZ5deCNYEc344kdi851oef028aTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","last_reissued_at":"2026-05-17T23:47:40.500609Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:40.500609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.11968","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":"2026-05-17T23:47:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcGtGa6W//lVjbVJZC+ypBgqeKL3+S+9smzsy+Tr/W2/eFLaNf9GGDb/MyVDyliI06yG6ccVbeW8ecW24VeuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:20:26.397123Z"},"content_sha256":"a9878e3c261088597d1c8962f613719426fc126b7533510c456a3b239a7b8a59","schema_version":"1.0","event_id":"sha256:a9878e3c261088597d1c8962f613719426fc126b7533510c456a3b239a7b8a59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2NEKVEI2CWOROWUZZVBCCGIMBX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Semantic Vector Representations of Source Code via a Siamese Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Zhang, David Wehr, Eleanor Pence, Guilherme Ferreira, Halley Fede, John Walczyk, Joseph Hughes","submitted_at":"2019-04-26T17:52:06Z","abstract_excerpt":"The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create vectors which capture the semantics of code. We evaluate the quality of embeddings by identifying which problem from a programming competition the code solves. Our model significantly outperforms a bag-of-tokens embedding, providing promising results for improving code embeddings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11968","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":""},"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":"2026-05-17T23:47:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a1GhvmF/5O+Lmt5HM3yGDBxzgyb68srQNsQWz7tHWtR5FV44ZumdjbdjfPyrpSjU3Kc8Od/WKjpcqeSStSNOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:20:26.397796Z"},"content_sha256":"f43ecebd252616409bd574a8b2c82ace0a250b5dadce56e40ca3b16a4c514a20","schema_version":"1.0","event_id":"sha256:f43ecebd252616409bd574a8b2c82ace0a250b5dadce56e40ca3b16a4c514a20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/bundle.json","state_url":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/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":"2026-05-29T15:20:26Z","links":{"resolver":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX","bundle":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/bundle.json","state":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2NEKVEI2CWOROWUZZVBCCGIMBX","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":"38d64fe52b74943d2d147cdd00b222e709131fc1be47514e0e3c8056776a1965","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-26T17:52:06Z","title_canon_sha256":"7b3c096edcae673e9a55f553ed92644f4d11810ef2d986e65f62e2b7f95ea562"},"schema_version":"1.0","source":{"id":"1904.11968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11968","created_at":"2026-05-17T23:47:40Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11968v1","created_at":"2026-05-17T23:47:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11968","created_at":"2026-05-17T23:47:40Z"},{"alias_kind":"pith_short_12","alias_value":"2NEKVEI2CWOR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2NEKVEI2CWOROWUZ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2NEKVEI2","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:f43ecebd252616409bd574a8b2c82ace0a250b5dadce56e40ca3b16a4c514a20","target":"graph","created_at":"2026-05-17T23:47:40Z","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"},"paper":{"abstract_excerpt":"The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create vectors which capture the semantics of code. We evaluate the quality of embeddings by identifying which problem from a programming competition the code solves. Our model significantly outperforms a bag-of-tokens embedding, providing promising results for improving code embeddings","authors_text":"Bo Zhang, David Wehr, Eleanor Pence, Guilherme Ferreira, Halley Fede, John Walczyk, Joseph Hughes","cross_cats":["cs.PL","cs.SE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-26T17:52:06Z","title":"Learning Semantic Vector Representations of Source Code via a Siamese Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11968","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:a9878e3c261088597d1c8962f613719426fc126b7533510c456a3b239a7b8a59","target":"record","created_at":"2026-05-17T23:47:40Z","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":"38d64fe52b74943d2d147cdd00b222e709131fc1be47514e0e3c8056776a1965","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-26T17:52:06Z","title_canon_sha256":"7b3c096edcae673e9a55f553ed92644f4d11810ef2d986e65f62e2b7f95ea562"},"schema_version":"1.0","source":{"id":"1904.11968","kind":"arxiv","version":1}},"canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","first_computed_at":"2026-05-17T23:47:40.500609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:40.500609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gw8ynr1aYrWz9Etwk5AKycm7WK7gSkg7gYg6nuFpr7dEF6s6fD5mvTWdypZ5deCNYEc344kdi851oef028aTAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:40.501155Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9878e3c261088597d1c8962f613719426fc126b7533510c456a3b239a7b8a59","sha256:f43ecebd252616409bd574a8b2c82ace0a250b5dadce56e40ca3b16a4c514a20"],"state_sha256":"edd567d70808c90a0f4dca4990853aa9d170dbf6f93856dfc7289f8b8ab2477e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYbmaXHJrK2HiuPkR9OAXrR2Yr09dLClAxc49K1ouk9VUmrPxYluV4pHpc9XxYWtnkEcRKFjG63B/x2VCSGwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:20:26.401089Z","bundle_sha256":"004f819fd8a45ac40dc64cdb6866e8dbda247e007d40a440ff546fae4839eb2e"}}