{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WSN66QMOQMTAT3RYYALACWS2SM","short_pith_number":"pith:WSN66QMO","schema_version":"1.0","canonical_sha256":"b49bef418e832609ee38c016015a5a9311d8ac37e56be09a68a469c6372024b0","source":{"kind":"arxiv","id":"2406.04344","version":3},"attestation_state":"computed","paper":{"title":"Verbalized Machine Learning: Revisiting Machine Learning with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Robert Bamler, Tim Z. Xiao, Weiyang Liu","submitted_at":"2024-06-06T17:59:56Z","abstract_excerpt":"Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) models that are typically optimized over a continuous parameter space, VML constrains the parameter space to be human-interpretable natural language. Such a constraint leads to a new perspective of function approximation, where an LLM with a text prompt can be viewed as a function parameterized by the text prompt. Guided by this perspective, we revisit classical ML problems, such as regression and classification, and "},"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":"2406.04344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T17:59:56Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"9aa7cc6f606649e40064146c4be344ce64d7a047304688df9cd6933bbd8088ff","abstract_canon_sha256":"9160bcf0fa25835765d2b2e4b71fa06847ecb346345c9aa7192669847915854d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:03.534471Z","signature_b64":"yFSZiQKqH+mW+XPIUHyeF4ci+U/seYeDQADFXxfp1pvMCTlG5TsCjgxxdzaFauj/pCyF8X92taY3I+9gGNlvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b49bef418e832609ee38c016015a5a9311d8ac37e56be09a68a469c6372024b0","last_reissued_at":"2026-07-05T10:14:03.533780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:03.533780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verbalized Machine Learning: Revisiting Machine Learning with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Robert Bamler, Tim Z. Xiao, Weiyang Liu","submitted_at":"2024-06-06T17:59:56Z","abstract_excerpt":"Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) models that are typically optimized over a continuous parameter space, VML constrains the parameter space to be human-interpretable natural language. Such a constraint leads to a new perspective of function approximation, where an LLM with a text prompt can be viewed as a function parameterized by the text prompt. Guided by this perspective, we revisit classical ML problems, such as regression and classification, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04344","kind":"arxiv","version":3},"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/2406.04344/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":"2406.04344","created_at":"2026-07-05T10:14:03.533857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04344v3","created_at":"2026-07-05T10:14:03.533857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04344","created_at":"2026-07-05T10:14:03.533857+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSN66QMOQMTA","created_at":"2026-07-05T10:14:03.533857+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSN66QMOQMTAT3RY","created_at":"2026-07-05T10:14:03.533857+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSN66QMO","created_at":"2026-07-05T10:14:03.533857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23116","citing_title":"CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM","json":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM.json","graph_json":"https://pith.science/api/pith-number/WSN66QMOQMTAT3RYYALACWS2SM/graph.json","events_json":"https://pith.science/api/pith-number/WSN66QMOQMTAT3RYYALACWS2SM/events.json","paper":"https://pith.science/paper/WSN66QMO"},"agent_actions":{"view_html":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM","download_json":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM.json","view_paper":"https://pith.science/paper/WSN66QMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04344&json=true","fetch_graph":"https://pith.science/api/pith-number/WSN66QMOQMTAT3RYYALACWS2SM/graph.json","fetch_events":"https://pith.science/api/pith-number/WSN66QMOQMTAT3RYYALACWS2SM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM/action/storage_attestation","attest_author":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM/action/author_attestation","sign_citation":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM/action/citation_signature","submit_replication":"https://pith.science/pith/WSN66QMOQMTAT3RYYALACWS2SM/action/replication_record"}},"created_at":"2026-07-05T10:14:03.533857+00:00","updated_at":"2026-07-05T10:14:03.533857+00:00"}