{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ON6SIJLQTULIVSLOROI2VZUOSK","short_pith_number":"pith:ON6SIJLQ","schema_version":"1.0","canonical_sha256":"737d2425709d168ac96e8b91aae68e92af4aaf40499a9151f3cb13df4410ba39","source":{"kind":"arxiv","id":"2006.05265","version":6},"attestation_state":"computed","paper":{"title":"MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anand Venkat, Fangke Ye, Jesmin Jahan Tithi, Justin Gottschlich, Nesime Tatbul, Niranjan Hasabnis, Paul Petersen, Pradeep Dubey, Ryan Marcus, Shengtian Zhou, Tim Kraska, Timothy Mattson, Vivek Sarkar","submitted_at":"2020-06-05T20:55:23Z","abstract_excerpt":"Code semantics similarity can be used for many tasks such as code recommendation, automated software defect correction, and clone detection. Yet, the accuracy of such systems has not yet reached a level of general purpose reliability. To help address this, we present Machine Inferred Code Similarity (MISIM), a neural code semantics similarity system consisting of two core components: (i)MISIM uses a novel context-aware semantics structure, which was purpose-built to lift semantics from code syntax; (ii)MISIM uses an extensible neural code similarity scoring algorithm, which can be used for var"},"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":"2006.05265","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-05T20:55:23Z","cross_cats_sorted":["cs.SE","stat.ML"],"title_canon_sha256":"7f928fd08e127ddbe74085bbbbe7ff3d07da560e7c02069aecc7f80d70ff9507","abstract_canon_sha256":"0610c5a7136a6ada00dbc7c2b714d8f1489256a100d241a8d7be4616a4f84e3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:47.986109Z","signature_b64":"TtwOto9tP3QM1A+5SOIe7zoC9HlU9iyFZaeAiuYwzJuSl2cT5EM5A2SEcKkEsjgwWNfY9RHyZVfe3GJzDLc6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"737d2425709d168ac96e8b91aae68e92af4aaf40499a9151f3cb13df4410ba39","last_reissued_at":"2026-07-05T02:45:47.985579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:47.985579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anand Venkat, Fangke Ye, Jesmin Jahan Tithi, Justin Gottschlich, Nesime Tatbul, Niranjan Hasabnis, Paul Petersen, Pradeep Dubey, Ryan Marcus, Shengtian Zhou, Tim Kraska, Timothy Mattson, Vivek Sarkar","submitted_at":"2020-06-05T20:55:23Z","abstract_excerpt":"Code semantics similarity can be used for many tasks such as code recommendation, automated software defect correction, and clone detection. Yet, the accuracy of such systems has not yet reached a level of general purpose reliability. To help address this, we present Machine Inferred Code Similarity (MISIM), a neural code semantics similarity system consisting of two core components: (i)MISIM uses a novel context-aware semantics structure, which was purpose-built to lift semantics from code syntax; (ii)MISIM uses an extensible neural code similarity scoring algorithm, which can be used for var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05265","kind":"arxiv","version":6},"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/2006.05265/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":"2006.05265","created_at":"2026-07-05T02:45:47.985638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05265v6","created_at":"2026-07-05T02:45:47.985638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05265","created_at":"2026-07-05T02:45:47.985638+00:00"},{"alias_kind":"pith_short_12","alias_value":"ON6SIJLQTULI","created_at":"2026-07-05T02:45:47.985638+00:00"},{"alias_kind":"pith_short_16","alias_value":"ON6SIJLQTULIVSLO","created_at":"2026-07-05T02:45:47.985638+00:00"},{"alias_kind":"pith_short_8","alias_value":"ON6SIJLQ","created_at":"2026-07-05T02:45:47.985638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2102.04664","citing_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK","json":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK.json","graph_json":"https://pith.science/api/pith-number/ON6SIJLQTULIVSLOROI2VZUOSK/graph.json","events_json":"https://pith.science/api/pith-number/ON6SIJLQTULIVSLOROI2VZUOSK/events.json","paper":"https://pith.science/paper/ON6SIJLQ"},"agent_actions":{"view_html":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK","download_json":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK.json","view_paper":"https://pith.science/paper/ON6SIJLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05265&json=true","fetch_graph":"https://pith.science/api/pith-number/ON6SIJLQTULIVSLOROI2VZUOSK/graph.json","fetch_events":"https://pith.science/api/pith-number/ON6SIJLQTULIVSLOROI2VZUOSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK/action/storage_attestation","attest_author":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK/action/author_attestation","sign_citation":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK/action/citation_signature","submit_replication":"https://pith.science/pith/ON6SIJLQTULIVSLOROI2VZUOSK/action/replication_record"}},"created_at":"2026-07-05T02:45:47.985638+00:00","updated_at":"2026-07-05T02:45:47.985638+00:00"}