{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6D6ZTQMH3NIGFN4A4UVKT5R273","short_pith_number":"pith:6D6ZTQMH","schema_version":"1.0","canonical_sha256":"f0fd99c187db5062b780e52aa9f63afef6d2c3c16e99f876cfeb5165a15cb83f","source":{"kind":"arxiv","id":"2201.01549","version":4},"attestation_state":"computed","paper":{"title":"SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bin Luo, Changan Niu, Chuanyi Li, Jidong Ge, Liguo Huang, Vincent Ng","submitted_at":"2022-01-05T11:26:53Z","abstract_excerpt":"Recent years have seen the successful application of large pre-trained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-ar"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.01549","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-01-05T11:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"2ca3a3c560f212fe9b84274c2f48ce185f564781abdaedb1c7a70aee34981ee1","abstract_canon_sha256":"59851efad052da4a2efe5bcce3c72b478c3e49f5d283cbf92f5d06fd70df776b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:21.792361Z","signature_b64":"VB6gr0bwZQkxQfq0YRboAOkjCPTM0G4F1QaZxM4wtIRrihWnnbscGRreslQaUuCkCxVfaTBQvP4qJY0T5C6LDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0fd99c187db5062b780e52aa9f63afef6d2c3c16e99f876cfeb5165a15cb83f","last_reissued_at":"2026-07-05T04:26:21.791843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:21.791843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bin Luo, Changan Niu, Chuanyi Li, Jidong Ge, Liguo Huang, Vincent Ng","submitted_at":"2022-01-05T11:26:53Z","abstract_excerpt":"Recent years have seen the successful application of large pre-trained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01549","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/2201.01549/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2201.01549","created_at":"2026-07-05T04:26:21.791896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01549v4","created_at":"2026-07-05T04:26:21.791896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01549","created_at":"2026-07-05T04:26:21.791896+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D6ZTQMH3NIG","created_at":"2026-07-05T04:26:21.791896+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D6ZTQMH3NIGFN4A","created_at":"2026-07-05T04:26:21.791896+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D6ZTQMH","created_at":"2026-07-05T04:26:21.791896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29901","citing_title":"Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273","json":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273.json","graph_json":"https://pith.science/api/pith-number/6D6ZTQMH3NIGFN4A4UVKT5R273/graph.json","events_json":"https://pith.science/api/pith-number/6D6ZTQMH3NIGFN4A4UVKT5R273/events.json","paper":"https://pith.science/paper/6D6ZTQMH"},"agent_actions":{"view_html":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273","download_json":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273.json","view_paper":"https://pith.science/paper/6D6ZTQMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01549&json=true","fetch_graph":"https://pith.science/api/pith-number/6D6ZTQMH3NIGFN4A4UVKT5R273/graph.json","fetch_events":"https://pith.science/api/pith-number/6D6ZTQMH3NIGFN4A4UVKT5R273/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273/action/storage_attestation","attest_author":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273/action/author_attestation","sign_citation":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273/action/citation_signature","submit_replication":"https://pith.science/pith/6D6ZTQMH3NIGFN4A4UVKT5R273/action/replication_record"}},"created_at":"2026-07-05T04:26:21.791896+00:00","updated_at":"2026-07-05T04:26:21.791896+00:00"}