{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQBCTJTIT7LU4LD2DEUFAUQOU5","short_pith_number":"pith:WQBCTJTI","schema_version":"1.0","canonical_sha256":"b40229a6689fd74e2c7a192850520ea7627cf592450e526d374e47145412ae1e","source":{"kind":"arxiv","id":"2407.02424","version":2},"attestation_state":"computed","paper":{"title":"A Pattern Language for Machine Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.CT"],"primary_cat":"cs.LG","authors_text":"Benjamin Rodatz, Ian Fan, Neil John Ortega, Thomas Hoffmann, Tuomas Laakkonen, Vincent Wang-Mascianica","submitted_at":"2024-07-02T16:50:27Z","abstract_excerpt":"We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints \"tasks\", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our"},"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":"2407.02424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T16:50:27Z","cross_cats_sorted":["math.CT"],"title_canon_sha256":"10b5de9127eb167e848a1ce688ae649049418807fc721d0886f244a1cf1a97e4","abstract_canon_sha256":"b4ddc734a66cfc369869bb0d63185e3c7914ade4178ba2e8c7bad391f1fc3642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:16.864575Z","signature_b64":"0HPypG3fAHIkTBBCE251bCWJ23FYYyHDajbzgKKiE31SdJcVWZrtKVF6jbRZnk9GOcbdRJeO0vfXwyC/2BX+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b40229a6689fd74e2c7a192850520ea7627cf592450e526d374e47145412ae1e","last_reissued_at":"2026-07-05T10:58:16.864015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:16.864015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Pattern Language for Machine Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.CT"],"primary_cat":"cs.LG","authors_text":"Benjamin Rodatz, Ian Fan, Neil John Ortega, Thomas Hoffmann, Tuomas Laakkonen, Vincent Wang-Mascianica","submitted_at":"2024-07-02T16:50:27Z","abstract_excerpt":"We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints \"tasks\", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02424","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/2407.02424/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":"2407.02424","created_at":"2026-07-05T10:58:16.864076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02424v2","created_at":"2026-07-05T10:58:16.864076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02424","created_at":"2026-07-05T10:58:16.864076+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQBCTJTIT7LU","created_at":"2026-07-05T10:58:16.864076+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQBCTJTIT7LU4LD2","created_at":"2026-07-05T10:58:16.864076+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQBCTJTI","created_at":"2026-07-05T10:58:16.864076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00558","citing_title":"A Methodology for Investigating AI Patterns Prevalence in Software Repositories","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08934","citing_title":"From Mechanistic to Compositional Interpretability","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5","json":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5.json","graph_json":"https://pith.science/api/pith-number/WQBCTJTIT7LU4LD2DEUFAUQOU5/graph.json","events_json":"https://pith.science/api/pith-number/WQBCTJTIT7LU4LD2DEUFAUQOU5/events.json","paper":"https://pith.science/paper/WQBCTJTI"},"agent_actions":{"view_html":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5","download_json":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5.json","view_paper":"https://pith.science/paper/WQBCTJTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02424&json=true","fetch_graph":"https://pith.science/api/pith-number/WQBCTJTIT7LU4LD2DEUFAUQOU5/graph.json","fetch_events":"https://pith.science/api/pith-number/WQBCTJTIT7LU4LD2DEUFAUQOU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5/action/storage_attestation","attest_author":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5/action/author_attestation","sign_citation":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5/action/citation_signature","submit_replication":"https://pith.science/pith/WQBCTJTIT7LU4LD2DEUFAUQOU5/action/replication_record"}},"created_at":"2026-07-05T10:58:16.864076+00:00","updated_at":"2026-07-05T10:58:16.864076+00:00"}