{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7CSV26MGIEJA65BCYLPIYCTVFD","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":"53ac649980c4566303a61c9b6c8fb1ef82fecd7dd3e3c2b804be5eb60e809457","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2021-10-08T02:56:43Z","title_canon_sha256":"ae5b885058f7743722494691a8ce8126b4de509bbcd97a6ede296a14c7b22f62"},"schema_version":"1.0","source":{"id":"2110.03868","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03868","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03868v2","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03868","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"7CSV26MGIEJA","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"7CSV26MGIEJA65BC","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"7CSV26MG","created_at":"2026-07-05T04:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:998f9d56863e4061d7a57baf9a98807246c57256b6416caca4ddc2b65ad138bf","target":"graph","created_at":"2026-07-05T04:06:45Z","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/2110.03868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the functional (dis)-similarity of source code is significant for code modeling tasks such as software vulnerability and code clone detection. We present DISCO(DIS-similarity of COde), a novel self-supervised model focusing on identifying (dis)similar functionalities of source code. Different from existing works, our approach does not require a huge amount of randomly collected datasets. Rather, we design structure-guided code transformation algorithms to generate synthetic code clones and inject real-world security bugs, augmenting the collected datasets in a targeted way. We pr","authors_text":"Alessandro Morari, Baishakhi Ray, Luca Buratti, Saikat Chakraborty, Saurabh Pujar, Yangruibo Ding","cross_cats":["cs.AI","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2021-10-08T02:56:43Z","title":"Towards Learning (Dis)-Similarity of Source Code from Program Contrasts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03868","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":"sha256:92ff1b9c8fe6bc90aa29569b97e5a37bd6ee05c60cc95462ee66c0e095710b41","target":"record","created_at":"2026-07-05T04:06:45Z","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":"53ac649980c4566303a61c9b6c8fb1ef82fecd7dd3e3c2b804be5eb60e809457","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2021-10-08T02:56:43Z","title_canon_sha256":"ae5b885058f7743722494691a8ce8126b4de509bbcd97a6ede296a14c7b22f62"},"schema_version":"1.0","source":{"id":"2110.03868","kind":"arxiv","version":2}},"canonical_sha256":"f8a55d798641120f7422c2de8c0a7528d6eed58c7d75aaa6c22aa2bdc57a1378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8a55d798641120f7422c2de8c0a7528d6eed58c7d75aaa6c22aa2bdc57a1378","first_computed_at":"2026-07-05T04:06:45.628811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:45.628811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aqBWl9PSsOEZ7Ev4n9BfiD2cbPzqICf0OlhnefvXtLG/P2aCOvw9q19Mv7mEuKqUbPnZnkhk24qcogaqPpc7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:45.629227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03868","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92ff1b9c8fe6bc90aa29569b97e5a37bd6ee05c60cc95462ee66c0e095710b41","sha256:998f9d56863e4061d7a57baf9a98807246c57256b6416caca4ddc2b65ad138bf"],"state_sha256":"fdd0e861afde2399670f0816aae32b84b1182d584e40b3f3fb720f690df9b0c3"}