{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:S7DNLQ5MSG6MEMQFSPBSYH7CTT","short_pith_number":"pith:S7DNLQ5M","canonical_record":{"source":{"id":"2105.08645","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-18T16:22:05Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"ef3baf7a3e3d32d5317fae4ea8a7dd58d513fe9d1a8ab196e2630172522f06ae","abstract_canon_sha256":"1c1b2e4e2d9cb7551e09191c8f18b941e0415ddbb44092661714af98fe023633"},"schema_version":"1.0"},"canonical_sha256":"97c6d5c3ac91bcc2320593c32c1fe29cfaee8f283249e09ccb581b204322c67a","source":{"kind":"arxiv","id":"2105.08645","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08645","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08645v4","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08645","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"S7DNLQ5MSG6M","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"S7DNLQ5MSG6MEMQF","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"S7DNLQ5M","created_at":"2026-07-05T02:50:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:S7DNLQ5MSG6MEMQFSPBSYH7CTT","target":"record","payload":{"canonical_record":{"source":{"id":"2105.08645","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-18T16:22:05Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"ef3baf7a3e3d32d5317fae4ea8a7dd58d513fe9d1a8ab196e2630172522f06ae","abstract_canon_sha256":"1c1b2e4e2d9cb7551e09191c8f18b941e0415ddbb44092661714af98fe023633"},"schema_version":"1.0"},"canonical_sha256":"97c6d5c3ac91bcc2320593c32c1fe29cfaee8f283249e09ccb581b204322c67a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:46.309483Z","signature_b64":"BnXYJmimd53OfKyqANr7HWXX84wWGWMVm4aEGDfQufWRp6lW7qUOYr0OwSB1uyLsU0NIb2nhkdwDELmj88Z+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c6d5c3ac91bcc2320593c32c1fe29cfaee8f283249e09ccb581b204322c67a","last_reissued_at":"2026-07-05T02:50:46.309094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:46.309094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.08645","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQxMrHC8zF7WdNWbyf6Lh06LwIy5rDt2SvZ1/foQk09IRovfgCb793sug9TsfiKvoCDQtloLkTDG+I7ClbPGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:09:52.534203Z"},"content_sha256":"513659c46f03017f953140832a884c6a7bfdad8edb982f7e8f67f7e05f3c019f","schema_version":"1.0","event_id":"sha256:513659c46f03017f953140832a884c6a7bfdad8edb982f7e8f67f7e05f3c019f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:S7DNLQ5MSG6MEMQFSPBSYH7CTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoTexT: Multi-task Learning with Code-Text Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.AI","authors_text":"Alec Peltekian, Daniel Le, Hieu Nguyen, Hieu Tran, James Anibal, Long Phan, Yanfang Ye","submitted_at":"2021-05-18T16:22:05Z","abstract_excerpt":"We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both \"bimodal\" and \"unimodal\" data. Here, bimodal data is the combination of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08645","kind":"arxiv","version":4},"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/2105.08645/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":"2026-07-05T02:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6y4GJ1VLIs1RMB0Dfqln+Bf04CgATFiLltIL/oAMsoPdnfqlKwMXQH4inQTqHeJlu8iwiSorrLZR/TFtDKAcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:09:52.534700Z"},"content_sha256":"91ca85bea1197ead4bb16743090417a6b7c3da6cf35d557e40ccd27aede0458a","schema_version":"1.0","event_id":"sha256:91ca85bea1197ead4bb16743090417a6b7c3da6cf35d557e40ccd27aede0458a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT/bundle.json","state_url":"https://pith.science/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT/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":"2026-08-09T06:09:52Z","links":{"resolver":"https://pith.science/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT","bundle":"https://pith.science/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT/bundle.json","state":"https://pith.science/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S7DNLQ5MSG6MEMQFSPBSYH7CTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S7DNLQ5MSG6MEMQFSPBSYH7CTT","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":"1c1b2e4e2d9cb7551e09191c8f18b941e0415ddbb44092661714af98fe023633","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-18T16:22:05Z","title_canon_sha256":"ef3baf7a3e3d32d5317fae4ea8a7dd58d513fe9d1a8ab196e2630172522f06ae"},"schema_version":"1.0","source":{"id":"2105.08645","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08645","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08645v4","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08645","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"S7DNLQ5MSG6M","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"S7DNLQ5MSG6MEMQF","created_at":"2026-07-05T02:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"S7DNLQ5M","created_at":"2026-07-05T02:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:91ca85bea1197ead4bb16743090417a6b7c3da6cf35d557e40ccd27aede0458a","target":"graph","created_at":"2026-07-05T02:50:46Z","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/2105.08645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using self-supervision, CoTexT is pre-trained on large programming language corpora to learn a general understanding of language and code. CoTexT supports downstream NL-PL tasks such as code summarizing/documentation, code generation, defect detection, and code debugging. We train CoTexT on different combinations of available PL corpus including both \"bimodal\" and \"unimodal\" data. Here, bimodal data is the combination of t","authors_text":"Alec Peltekian, Daniel Le, Hieu Nguyen, Hieu Tran, James Anibal, Long Phan, Yanfang Ye","cross_cats":["cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-18T16:22:05Z","title":"CoTexT: Multi-task Learning with Code-Text Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08645","kind":"arxiv","version":4},"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":"sha256:513659c46f03017f953140832a884c6a7bfdad8edb982f7e8f67f7e05f3c019f","target":"record","created_at":"2026-07-05T02:50:46Z","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":"1c1b2e4e2d9cb7551e09191c8f18b941e0415ddbb44092661714af98fe023633","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-18T16:22:05Z","title_canon_sha256":"ef3baf7a3e3d32d5317fae4ea8a7dd58d513fe9d1a8ab196e2630172522f06ae"},"schema_version":"1.0","source":{"id":"2105.08645","kind":"arxiv","version":4}},"canonical_sha256":"97c6d5c3ac91bcc2320593c32c1fe29cfaee8f283249e09ccb581b204322c67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97c6d5c3ac91bcc2320593c32c1fe29cfaee8f283249e09ccb581b204322c67a","first_computed_at":"2026-07-05T02:50:46.309094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:46.309094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BnXYJmimd53OfKyqANr7HWXX84wWGWMVm4aEGDfQufWRp6lW7qUOYr0OwSB1uyLsU0NIb2nhkdwDELmj88Z+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:46.309483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.08645","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:513659c46f03017f953140832a884c6a7bfdad8edb982f7e8f67f7e05f3c019f","sha256:91ca85bea1197ead4bb16743090417a6b7c3da6cf35d557e40ccd27aede0458a"],"state_sha256":"1fb57b74619cbda5c9aabebfc52376b4cf3ca9887da6dc067dfe5320c65c9e2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vaUpOYLlg3WM3DsozlkWx/OpYd9PYjK3Hvkzllo7EUrzZRg/Y3nwBLOCYqXqBnv7JTTrri8g5G+cA7oKNnwvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:09:52.539723Z","bundle_sha256":"5e8a781950d6a7151512a6950aefabc9d9ff9e049a2e198df5a7d698c06582ce"}}