{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EETLHSRPBOI5ZOZLG6BNJAC7OG","short_pith_number":"pith:EETLHSRP","schema_version":"1.0","canonical_sha256":"2126b3ca2f0b91dcbb2b3782d4805f71b9ab7c027e025f1ef13e8cca17edde06","source":{"kind":"arxiv","id":"2402.15351","version":2},"attestation_state":"computed","paper":{"title":"AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chen Qian, Ping Luo, Sheng Jin, Wang Zeng, Wentao Liu, Zekang Yang","submitted_at":"2024-02-23T14:38:19Z","abstract_excerpt":"Automated machine learning (AutoML) is a collection of techniques designed to automate the machine learning development process. While traditional AutoML approaches have been successfully applied in several critical steps of model development (e.g. hyperparameter optimization), there lacks a AutoML system that automates the entire end-to-end model production workflow for computer vision. To fill this blank, we propose a novel request-to-model task, which involves understanding the user's natural language request and execute the entire workflow to output production-ready models. This empowers n"},"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":"2402.15351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T14:38:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2a7dfe7e26d0accb4f223450db6d06685866038d9fbe9fafdc12c9cabbdd0421","abstract_canon_sha256":"a980513dc54956f197864be21558ac882edde4b863533968430599d18260ae73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:25.053231Z","signature_b64":"fleEvRrHlW2yao57n79dzI+mZxtmDBwVEehhj2gJU9d9BJH3DDsLNdyy4FlJrseuYf92oSYVTuK2BnUnaz1kAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2126b3ca2f0b91dcbb2b3782d4805f71b9ab7c027e025f1ef13e8cca17edde06","last_reissued_at":"2026-07-05T09:54:25.052748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:25.052748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chen Qian, Ping Luo, Sheng Jin, Wang Zeng, Wentao Liu, Zekang Yang","submitted_at":"2024-02-23T14:38:19Z","abstract_excerpt":"Automated machine learning (AutoML) is a collection of techniques designed to automate the machine learning development process. While traditional AutoML approaches have been successfully applied in several critical steps of model development (e.g. hyperparameter optimization), there lacks a AutoML system that automates the entire end-to-end model production workflow for computer vision. To fill this blank, we propose a novel request-to-model task, which involves understanding the user's natural language request and execute the entire workflow to output production-ready models. This empowers n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15351","kind":"arxiv","version":2},"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/2402.15351/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":"2402.15351","created_at":"2026-07-05T09:54:25.052808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15351v2","created_at":"2026-07-05T09:54:25.052808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15351","created_at":"2026-07-05T09:54:25.052808+00:00"},{"alias_kind":"pith_short_12","alias_value":"EETLHSRPBOI5","created_at":"2026-07-05T09:54:25.052808+00:00"},{"alias_kind":"pith_short_16","alias_value":"EETLHSRPBOI5ZOZL","created_at":"2026-07-05T09:54:25.052808+00:00"},{"alias_kind":"pith_short_8","alias_value":"EETLHSRP","created_at":"2026-07-05T09:54:25.052808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20728","citing_title":"VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG","json":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG.json","graph_json":"https://pith.science/api/pith-number/EETLHSRPBOI5ZOZLG6BNJAC7OG/graph.json","events_json":"https://pith.science/api/pith-number/EETLHSRPBOI5ZOZLG6BNJAC7OG/events.json","paper":"https://pith.science/paper/EETLHSRP"},"agent_actions":{"view_html":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG","download_json":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG.json","view_paper":"https://pith.science/paper/EETLHSRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15351&json=true","fetch_graph":"https://pith.science/api/pith-number/EETLHSRPBOI5ZOZLG6BNJAC7OG/graph.json","fetch_events":"https://pith.science/api/pith-number/EETLHSRPBOI5ZOZLG6BNJAC7OG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG/action/storage_attestation","attest_author":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG/action/author_attestation","sign_citation":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG/action/citation_signature","submit_replication":"https://pith.science/pith/EETLHSRPBOI5ZOZLG6BNJAC7OG/action/replication_record"}},"created_at":"2026-07-05T09:54:25.052808+00:00","updated_at":"2026-07-05T09:54:25.052808+00:00"}