{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6B6I4EMADU6DPSQSN5FFD3M3L6","short_pith_number":"pith:6B6I4EMA","schema_version":"1.0","canonical_sha256":"f07c8e11801d3c37ca126f4a51ed9b5fb548221c080b889ad6a5045802ca5ae0","source":{"kind":"arxiv","id":"1905.11445","version":1},"attestation_state":"computed","paper":{"title":"COSET: A Benchmark for Evaluating Neural Program Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ke Wang, Mihai Christodorescu","submitted_at":"2019-05-27T18:44:54Z","abstract_excerpt":"Neural program embedding can be helpful in analyzing large software, a task that is challenging for traditional logic-based program analyses due to their limited scalability. A key focus of recent machine-learning advances in this area is on modeling program semantics instead of just syntax. Unfortunately evaluating such advances is not obvious, as program semantics does not lend itself to straightforward metrics. In this paper, we introduce a benchmarking framework called COSET for standardizing the evaluation of neural program embeddings. COSET consists of a diverse dataset of programs in so"},"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":"1905.11445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T18:44:54Z","cross_cats_sorted":["cs.PL","stat.ML"],"title_canon_sha256":"8d84fba38a2c024909cf1977ec710f74cd646da238e84aaf26a48de93094d678","abstract_canon_sha256":"0dfbd6ea6a4ec38006b22ed82abd8b6b6365880ade4c0a62cfc645cc28b054e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.395640Z","signature_b64":"Ww2ccXeCed5lej1e7GKIL8to+6xjcdT6YGXE2a5kKwPRH5aTk9Z3GnmDPA8venjoWUO7XErI7YLqOy9qHlifDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f07c8e11801d3c37ca126f4a51ed9b5fb548221c080b889ad6a5045802ca5ae0","last_reissued_at":"2026-05-17T23:44:53.395069Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.395069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COSET: A Benchmark for Evaluating Neural Program Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ke Wang, Mihai Christodorescu","submitted_at":"2019-05-27T18:44:54Z","abstract_excerpt":"Neural program embedding can be helpful in analyzing large software, a task that is challenging for traditional logic-based program analyses due to their limited scalability. A key focus of recent machine-learning advances in this area is on modeling program semantics instead of just syntax. Unfortunately evaluating such advances is not obvious, as program semantics does not lend itself to straightforward metrics. In this paper, we introduce a benchmarking framework called COSET for standardizing the evaluation of neural program embeddings. COSET consists of a diverse dataset of programs in so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11445","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.11445","created_at":"2026-05-17T23:44:53.395148+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11445v1","created_at":"2026-05-17T23:44:53.395148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11445","created_at":"2026-05-17T23:44:53.395148+00:00"},{"alias_kind":"pith_short_12","alias_value":"6B6I4EMADU6D","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6B6I4EMADU6DPSQS","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6B6I4EMA","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02136","citing_title":"Learning Blended, Precise Semantic Program Embeddings","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6","json":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6.json","graph_json":"https://pith.science/api/pith-number/6B6I4EMADU6DPSQSN5FFD3M3L6/graph.json","events_json":"https://pith.science/api/pith-number/6B6I4EMADU6DPSQSN5FFD3M3L6/events.json","paper":"https://pith.science/paper/6B6I4EMA"},"agent_actions":{"view_html":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6","download_json":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6.json","view_paper":"https://pith.science/paper/6B6I4EMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11445&json=true","fetch_graph":"https://pith.science/api/pith-number/6B6I4EMADU6DPSQSN5FFD3M3L6/graph.json","fetch_events":"https://pith.science/api/pith-number/6B6I4EMADU6DPSQSN5FFD3M3L6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6/action/storage_attestation","attest_author":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6/action/author_attestation","sign_citation":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6/action/citation_signature","submit_replication":"https://pith.science/pith/6B6I4EMADU6DPSQSN5FFD3M3L6/action/replication_record"}},"created_at":"2026-05-17T23:44:53.395148+00:00","updated_at":"2026-05-17T23:44:53.395148+00:00"}