{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5AEWQ7VW3RUCBW6NQC5B5IIZFX","short_pith_number":"pith:5AEWQ7VW","canonical_record":{"source":{"id":"2010.12663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-10-23T20:52:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f6f25ffc693b816de922af08d102c89026d2d54e1b001c8c578eb3b8aa4bf917","abstract_canon_sha256":"804b58eaf697383b349d58522e13d1e6d4979e52a5f683798f994e898dab0daa"},"schema_version":"1.0"},"canonical_sha256":"e809687eb6dc6820dbcd80ba1ea1192dea618bb359d58a2b0449765c7c79b288","source":{"kind":"arxiv","id":"2010.12663","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12663","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12663v2","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12663","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"pith_short_12","alias_value":"5AEWQ7VW3RUC","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"pith_short_16","alias_value":"5AEWQ7VW3RUCBW6N","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"pith_short_8","alias_value":"5AEWQ7VW","created_at":"2026-07-05T02:35:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5AEWQ7VW3RUCBW6NQC5B5IIZFX","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-10-23T20:52:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f6f25ffc693b816de922af08d102c89026d2d54e1b001c8c578eb3b8aa4bf917","abstract_canon_sha256":"804b58eaf697383b349d58522e13d1e6d4979e52a5f683798f994e898dab0daa"},"schema_version":"1.0"},"canonical_sha256":"e809687eb6dc6820dbcd80ba1ea1192dea618bb359d58a2b0449765c7c79b288","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:20.176540Z","signature_b64":"+x/hRkePKXCBlpweRB22g4+beBVGjhJ8R7E2liumtxXSrNtEFZx/1vDPonYNF9NO8DSp6a8NwQQxPP8idDoKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e809687eb6dc6820dbcd80ba1ea1192dea618bb359d58a2b0449765c7c79b288","last_reissued_at":"2026-07-05T02:35:20.176129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:20.176129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12663","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:35:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eiEFtreZmEU/vFxY8VvFD0fYblev2uRNr9z9u1vYJEW6jv8MxsihpTT3zXwFSdt9yEpuf0Emqn+zrHcuJEa5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:03.870246Z"},"content_sha256":"5cd13d72242f31d68edc9614bebe3d992d4a09da6e52509eec5c6f5919866636","schema_version":"1.0","event_id":"sha256:5cd13d72242f31d68edc9614bebe3d992d4a09da6e52509eec5c6f5919866636"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5AEWQ7VW3RUCBW6NQC5B5IIZFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Nadezhda Chirkova, Sergey Troshin","submitted_at":"2020-10-23T20:52:46Z","abstract_excerpt":"There is an emerging interest in the application of natural language processing models to source code processing tasks. One of the major problems in applying deep learning to software engineering is that source code often contains a lot of rare identifiers, resulting in huge vocabularies. We propose a simple, yet effective method, based on identifier anonymization, to handle out-of-vocabulary (OOV) identifiers. Our method can be treated as a preprocessing step and, therefore, allows for easy implementation. We show that the proposed OOV anonymization method significantly improves the performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12663","kind":"arxiv","version":2},"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/2010.12663/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":"2026-07-05T02:35:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FnNeOlXK3Dp2hunSCQJcIAIRm6uBNbpJkJSYIqcrkhvtRxzrW3kaev5BCRIe9SSJkkRcPx5VETitiJvmdnsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:03.870577Z"},"content_sha256":"e194423e378f288affe37fb944b590a72f98bbceaf15e26701178af51a93f920","schema_version":"1.0","event_id":"sha256:e194423e378f288affe37fb944b590a72f98bbceaf15e26701178af51a93f920"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX/bundle.json","state_url":"https://pith.science/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX/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":"2026-08-06T01:14:03Z","links":{"resolver":"https://pith.science/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX","bundle":"https://pith.science/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX/bundle.json","state":"https://pith.science/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AEWQ7VW3RUCBW6NQC5B5IIZFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5AEWQ7VW3RUCBW6NQC5B5IIZFX","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":"804b58eaf697383b349d58522e13d1e6d4979e52a5f683798f994e898dab0daa","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-10-23T20:52:46Z","title_canon_sha256":"f6f25ffc693b816de922af08d102c89026d2d54e1b001c8c578eb3b8aa4bf917"},"schema_version":"1.0","source":{"id":"2010.12663","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12663","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12663v2","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12663","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"pith_short_12","alias_value":"5AEWQ7VW3RUC","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"pith_short_16","alias_value":"5AEWQ7VW3RUCBW6N","created_at":"2026-07-05T02:35:20Z"},{"alias_kind":"pith_short_8","alias_value":"5AEWQ7VW","created_at":"2026-07-05T02:35:20Z"}],"graph_snapshots":[{"event_id":"sha256:e194423e378f288affe37fb944b590a72f98bbceaf15e26701178af51a93f920","target":"graph","created_at":"2026-07-05T02:35:20Z","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/2010.12663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is an emerging interest in the application of natural language processing models to source code processing tasks. One of the major problems in applying deep learning to software engineering is that source code often contains a lot of rare identifiers, resulting in huge vocabularies. We propose a simple, yet effective method, based on identifier anonymization, to handle out-of-vocabulary (OOV) identifiers. Our method can be treated as a preprocessing step and, therefore, allows for easy implementation. We show that the proposed OOV anonymization method significantly improves the performan","authors_text":"Nadezhda Chirkova, Sergey Troshin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-10-23T20:52:46Z","title":"A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12663","kind":"arxiv","version":2},"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":"sha256:5cd13d72242f31d68edc9614bebe3d992d4a09da6e52509eec5c6f5919866636","target":"record","created_at":"2026-07-05T02:35:20Z","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":"804b58eaf697383b349d58522e13d1e6d4979e52a5f683798f994e898dab0daa","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-10-23T20:52:46Z","title_canon_sha256":"f6f25ffc693b816de922af08d102c89026d2d54e1b001c8c578eb3b8aa4bf917"},"schema_version":"1.0","source":{"id":"2010.12663","kind":"arxiv","version":2}},"canonical_sha256":"e809687eb6dc6820dbcd80ba1ea1192dea618bb359d58a2b0449765c7c79b288","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e809687eb6dc6820dbcd80ba1ea1192dea618bb359d58a2b0449765c7c79b288","first_computed_at":"2026-07-05T02:35:20.176129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:35:20.176129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+x/hRkePKXCBlpweRB22g4+beBVGjhJ8R7E2liumtxXSrNtEFZx/1vDPonYNF9NO8DSp6a8NwQQxPP8idDoKAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:35:20.176540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12663","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cd13d72242f31d68edc9614bebe3d992d4a09da6e52509eec5c6f5919866636","sha256:e194423e378f288affe37fb944b590a72f98bbceaf15e26701178af51a93f920"],"state_sha256":"ee6d1f7749b05649e2dd190b3e17456773463f6c387a6a72b46ba3f20c0070d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfDvdneZp7P3PlaPP1uqDzW5dnLmIPOAd3MjAu9Rr54HsQ99Ab5J5QN3pIC2ihwEIsyf65N8Qg/p9IOlMSaGBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:14:03.873713Z","bundle_sha256":"754e08cf1895fd4c32aa43827d020c85a74cb543312470799bbe1265089b9ef4"}}