{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SKBEEKAFPRYHWIXLRJZQMMGCQ","short_pith_number":"pith:4SKBEEKA","schema_version":"1.0","canonical_sha256":"e4941211402be383d9175c53983186143942be00964cc9a9ee9b074aade03204","source":{"kind":"arxiv","id":"2506.04965","version":1},"attestation_state":"computed","paper":{"title":"From Struggle (06-2024) to Mastery (02-2025) LLMs Conquer Advanced Algorithm Exams and Pave the Way for Editorial Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adrian Marius Dumitran, Theodor-Pierre Moroianu, Vasile Paul Alexe","submitted_at":"2025-06-05T12:41:20Z","abstract_excerpt":"This paper presents a comprehensive evaluation of the performance of state-of-the-art Large Language Models (LLMs) on challenging university-level algorithms exams. By testing multiple models on both a Romanian exam and its high-quality English translation, we analyze LLMs' problem-solving capabilities, consistency, and multilingual performance. Our empirical study reveals that the most recent models not only achieve scores comparable to top-performing students but also demonstrate robust reasoning skills on complex, multi-step algorithmic challenges, even though difficulties remain with graph"},"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":"2506.04965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T12:41:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ba10758f01ef0d1b5c6ec216dc0bff225ec58cabd9f711021b66396611b1a48","abstract_canon_sha256":"78e0fe68d5bd3e8d947d463bf3eb40f0a2de52fce5431cde2d1e11b42a3d4577"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:39.806891Z","signature_b64":"f24GYK3ManLPNJztftDoV5vDvWYLxVid61rYhj59bi9w8sYk2tCrL3URn2Etm8AZWY+FEi3T5lQT/irMU42eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4941211402be383d9175c53983186143942be00964cc9a9ee9b074aade03204","last_reissued_at":"2026-07-05T11:16:39.806390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:39.806390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Struggle (06-2024) to Mastery (02-2025) LLMs Conquer Advanced Algorithm Exams and Pave the Way for Editorial Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adrian Marius Dumitran, Theodor-Pierre Moroianu, Vasile Paul Alexe","submitted_at":"2025-06-05T12:41:20Z","abstract_excerpt":"This paper presents a comprehensive evaluation of the performance of state-of-the-art Large Language Models (LLMs) on challenging university-level algorithms exams. By testing multiple models on both a Romanian exam and its high-quality English translation, we analyze LLMs' problem-solving capabilities, consistency, and multilingual performance. Our empirical study reveals that the most recent models not only achieve scores comparable to top-performing students but also demonstrate robust reasoning skills on complex, multi-step algorithmic challenges, even though difficulties remain with graph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04965","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.04965/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":"2506.04965","created_at":"2026-07-05T11:16:39.806458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04965v1","created_at":"2026-07-05T11:16:39.806458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04965","created_at":"2026-07-05T11:16:39.806458+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SKBEEKAFPRY","created_at":"2026-07-05T11:16:39.806458+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SKBEEKAFPRYHWIX","created_at":"2026-07-05T11:16:39.806458+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SKBEEKA","created_at":"2026-07-05T11:16:39.806458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ","json":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ.json","graph_json":"https://pith.science/api/pith-number/4SKBEEKAFPRYHWIXLRJZQMMGCQ/graph.json","events_json":"https://pith.science/api/pith-number/4SKBEEKAFPRYHWIXLRJZQMMGCQ/events.json","paper":"https://pith.science/paper/4SKBEEKA"},"agent_actions":{"view_html":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ","download_json":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ.json","view_paper":"https://pith.science/paper/4SKBEEKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04965&json=true","fetch_graph":"https://pith.science/api/pith-number/4SKBEEKAFPRYHWIXLRJZQMMGCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4SKBEEKAFPRYHWIXLRJZQMMGCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ/action/storage_attestation","attest_author":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ/action/author_attestation","sign_citation":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ/action/citation_signature","submit_replication":"https://pith.science/pith/4SKBEEKAFPRYHWIXLRJZQMMGCQ/action/replication_record"}},"created_at":"2026-07-05T11:16:39.806458+00:00","updated_at":"2026-07-05T11:16:39.806458+00:00"}