{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XI4ECRM4IDJIN5JIY3YYEH262A","short_pith_number":"pith:XI4ECRM4","schema_version":"1.0","canonical_sha256":"ba3841459c40d286f528c6f1821f5ed027cb39262f57cfe33fe087e105e5dce5","source":{"kind":"arxiv","id":"2605.17046","version":1},"attestation_state":"computed","paper":{"title":"1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anna B\\\"o{\\ss}end\\\"orfer, Fabian Deuser, Konrad Habel, Norbert Oswald, Robin-Nico Kampa","submitted_at":"2026-05-16T15:35:22Z","abstract_excerpt":"Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardized benchmark exists to evaluate their ability to design, implement, and train models from scratch across diverse domains. We introduce **1GC-7RC** (*Single Graphic Card: Seven Research Challenges*), a benchmark comprising seven ML tasks spanning language modeling, image classification, semantic segmentation, graph learning, tabular prediction, time-series forecasting, and text classification. Each task provides a locked data-preparation and evalu"},"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":"2605.17046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T15:35:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e000e31186cba0bd66b6b908ea7e25f1da802eaae446a67e3d0e6825df0f678f","abstract_canon_sha256":"c2854307fc73bec2e7cca23faeb72863accfea961e70c0410a8c5de5ac569898"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:37.733788Z","signature_b64":"8ntm3Rp23186EQnYcIQqV3t5wXwHPbzy2Jz66ZddqzdijiIPrJ3oIlXsKAs5+CjQldUX6ewwDSo37R78WKwWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba3841459c40d286f528c6f1821f5ed027cb39262f57cfe33fe087e105e5dce5","last_reissued_at":"2026-05-20T00:03:37.732894Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:37.732894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anna B\\\"o{\\ss}end\\\"orfer, Fabian Deuser, Konrad Habel, Norbert Oswald, Robin-Nico Kampa","submitted_at":"2026-05-16T15:35:22Z","abstract_excerpt":"Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardized benchmark exists to evaluate their ability to design, implement, and train models from scratch across diverse domains. We introduce **1GC-7RC** (*Single Graphic Card: Seven Research Challenges*), a benchmark comprising seven ML tasks spanning language modeling, image classification, semantic segmentation, graph learning, tabular prediction, time-series forecasting, and text classification. Each task provides a locked data-preparation and evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17046","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/2605.17046/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.829400Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.772969Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"50513d3f798a65cadb8cb01cfd8a9dfb2aae180d9a9c326c5c418e3a360d81a1"},"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":"2605.17046","created_at":"2026-05-20T00:03:37.733071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17046v1","created_at":"2026-05-20T00:03:37.733071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17046","created_at":"2026-05-20T00:03:37.733071+00:00"},{"alias_kind":"pith_short_12","alias_value":"XI4ECRM4IDJI","created_at":"2026-05-20T00:03:37.733071+00:00"},{"alias_kind":"pith_short_16","alias_value":"XI4ECRM4IDJIN5JI","created_at":"2026-05-20T00:03:37.733071+00:00"},{"alias_kind":"pith_short_8","alias_value":"XI4ECRM4","created_at":"2026-05-20T00:03:37.733071+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/XI4ECRM4IDJIN5JIY3YYEH262A","json":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A.json","graph_json":"https://pith.science/api/pith-number/XI4ECRM4IDJIN5JIY3YYEH262A/graph.json","events_json":"https://pith.science/api/pith-number/XI4ECRM4IDJIN5JIY3YYEH262A/events.json","paper":"https://pith.science/paper/XI4ECRM4"},"agent_actions":{"view_html":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A","download_json":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A.json","view_paper":"https://pith.science/paper/XI4ECRM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17046&json=true","fetch_graph":"https://pith.science/api/pith-number/XI4ECRM4IDJIN5JIY3YYEH262A/graph.json","fetch_events":"https://pith.science/api/pith-number/XI4ECRM4IDJIN5JIY3YYEH262A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A/action/storage_attestation","attest_author":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A/action/author_attestation","sign_citation":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A/action/citation_signature","submit_replication":"https://pith.science/pith/XI4ECRM4IDJIN5JIY3YYEH262A/action/replication_record"}},"created_at":"2026-05-20T00:03:37.733071+00:00","updated_at":"2026-05-20T00:03:37.733071+00:00"}