{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:36V5RF6QNQDJQEN2CNJRDLD7BD","short_pith_number":"pith:36V5RF6Q","canonical_record":{"source":{"id":"1904.03061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T13:37:42Z","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"title_canon_sha256":"613065e98e7b35f64dcf555f292a21f9875e26214249e47a2406d98e9e94e880","abstract_canon_sha256":"47fa342cf604ec6275339df888ff33dd5d13fc65b642589011ea5d72f308fd1e"},"schema_version":"1.0"},"canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","source":{"kind":"arxiv","id":"1904.03061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03061","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03061v1","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03061","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"36V5RF6QNQDJ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"36V5RF6QNQDJQEN2","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"36V5RF6Q","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:36V5RF6QNQDJQEN2CNJRDLD7BD","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T13:37:42Z","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"title_canon_sha256":"613065e98e7b35f64dcf555f292a21f9875e26214249e47a2406d98e9e94e880","abstract_canon_sha256":"47fa342cf604ec6275339df888ff33dd5d13fc65b642589011ea5d72f308fd1e"},"schema_version":"1.0"},"canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:18.729633Z","signature_b64":"MdeHfCq8BgJaEtRwo17d5g/37RBbMfo+xlB/KmrLTDCy1MDqv0XjL884YmQFRzZCMKLXq+Z6wFVPjjAxLsmoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","last_reissued_at":"2026-05-17T23:49:18.729091Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:18.729091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03061","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":"2026-05-17T23:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VflSk/KWOxgtpNijafIgPnx4JP7p0D/RHCBqD4WNifvrZCnyfGHrwRdRsHgrNqClUquKxf5CZC8MCqs3aQBRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:34:12.502021Z"},"content_sha256":"03fbcdc392b430b8ffd0c631f31822d782e53819e0138615d171011a221b7260","schema_version":"1.0","event_id":"sha256:03fbcdc392b430b8ffd0c631f31822d782e53819e0138615d171011a221b7260"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:36V5RF6QNQDJQEN2CNJRDLD7BD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Literature Study of Embeddings on Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Monperrus, Zimin Chen","submitted_at":"2019-04-05T13:37:42Z","abstract_excerpt":"Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The articles in this survey have been collected by asking authors of related work and with an extensive search on Google Scholar. Each article is categorized into five categories: 1. embedding of tokens 2. embedding of functions or methods 3. embedding of sequences or sets of method c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03061","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":"2026-05-17T23:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rCi5M9eau3oVMzvlKxNUpzCtZFWEmlLGWm509C6UdGoRwBd/SmGLEfMDCrAsI2j4cjASDNqxdZyJJV1jVlQmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:34:12.502396Z"},"content_sha256":"2df5dcf3fbb15cf1a4392f1c7df2b3354928a1a2a43ddf75dbaa1bade305bac2","schema_version":"1.0","event_id":"sha256:2df5dcf3fbb15cf1a4392f1c7df2b3354928a1a2a43ddf75dbaa1bade305bac2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/bundle.json","state_url":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/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":"2026-06-01T07:34:12Z","links":{"resolver":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD","bundle":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/bundle.json","state":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:36V5RF6QNQDJQEN2CNJRDLD7BD","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":"47fa342cf604ec6275339df888ff33dd5d13fc65b642589011ea5d72f308fd1e","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T13:37:42Z","title_canon_sha256":"613065e98e7b35f64dcf555f292a21f9875e26214249e47a2406d98e9e94e880"},"schema_version":"1.0","source":{"id":"1904.03061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03061","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03061v1","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03061","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"36V5RF6QNQDJ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"36V5RF6QNQDJQEN2","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"36V5RF6Q","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:2df5dcf3fbb15cf1a4392f1c7df2b3354928a1a2a43ddf75dbaa1bade305bac2","target":"graph","created_at":"2026-05-17T23:49:18Z","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":"Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The articles in this survey have been collected by asking authors of related work and with an extensive search on Google Scholar. Each article is categorized into five categories: 1. embedding of tokens 2. embedding of functions or methods 3. embedding of sequences or sets of method c","authors_text":"Martin Monperrus, Zimin Chen","cross_cats":["cs.PL","cs.SE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T13:37:42Z","title":"A Literature Study of Embeddings on Source Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03061","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":"sha256:03fbcdc392b430b8ffd0c631f31822d782e53819e0138615d171011a221b7260","target":"record","created_at":"2026-05-17T23:49:18Z","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":"47fa342cf604ec6275339df888ff33dd5d13fc65b642589011ea5d72f308fd1e","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T13:37:42Z","title_canon_sha256":"613065e98e7b35f64dcf555f292a21f9875e26214249e47a2406d98e9e94e880"},"schema_version":"1.0","source":{"id":"1904.03061","kind":"arxiv","version":1}},"canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","first_computed_at":"2026-05-17T23:49:18.729091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:18.729091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MdeHfCq8BgJaEtRwo17d5g/37RBbMfo+xlB/KmrLTDCy1MDqv0XjL884YmQFRzZCMKLXq+Z6wFVPjjAxLsmoBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:18.729633Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03fbcdc392b430b8ffd0c631f31822d782e53819e0138615d171011a221b7260","sha256:2df5dcf3fbb15cf1a4392f1c7df2b3354928a1a2a43ddf75dbaa1bade305bac2"],"state_sha256":"2caa68ee2d80fe93c17b8a6208271c75ed4350b780566c8006272b19be438b84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CH1kOsnCcQxY7tW85YNLiBnWAziTAF/7IRzexo5F9pq2fF0coSt7nxXdPFAnpMQey0+4bqMmwv0BJwR8n5odBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:34:12.504379Z","bundle_sha256":"5fc2937b54fb86bcbb2b0a29ee783d5c1b6fe3dfded1e1bc363589a043eb0b99"}}