{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NGSGLSUSSIGT6PAJNUUWBANKOO","short_pith_number":"pith:NGSGLSUS","schema_version":"1.0","canonical_sha256":"69a465ca92920d3f3c096d296081aa739717b82f04c0f84aeb2b7a917f8f73e4","source":{"kind":"arxiv","id":"1805.08809","version":3},"attestation_state":"computed","paper":{"title":"Infinite-Task Learning with RKHSs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lambert, Florence d'Alch\\'e-Buc, Maxime Sangnier, Romain Brault, Zolt\\'an Szab\\'o","submitted_at":"2018-05-22T18:38:59Z","abstract_excerpt":"Machine learning has witnessed tremendous success in solving tasks depending on a single hyperparameter. When considering simultaneously a finite number of tasks, multi-task learning enables one to account for the similarities of the tasks via appropriate regularizers. A step further consists of learning a continuum of tasks for various loss functions. A promising approach, called \\emph{Parametric Task Learning}, has paved the way in the continuum setting for affine models and piecewise-linear loss functions. In this work, we introduce a novel approach called \\emph{Infinite Task Learning} whos"},"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":"1805.08809","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T18:38:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46ef831404b35b8690213dbcd8a12599494d82b377a3a843213727d3afd475d3","abstract_canon_sha256":"664a0ba8adbb62d1fbddc71d5666b8f839a321065c1e8d830f6e93c0f0c41359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:36.850696Z","signature_b64":"4cQxk77yDVAioJD/+TWJG51LzaPrRmASrE4czW8hjhxSquBdGR/pSN22xEZI+6mfAs9afcxO3tBElrqQsAFCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69a465ca92920d3f3c096d296081aa739717b82f04c0f84aeb2b7a917f8f73e4","last_reissued_at":"2026-05-18T00:03:36.850125Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:36.850125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infinite-Task Learning with RKHSs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lambert, Florence d'Alch\\'e-Buc, Maxime Sangnier, Romain Brault, Zolt\\'an Szab\\'o","submitted_at":"2018-05-22T18:38:59Z","abstract_excerpt":"Machine learning has witnessed tremendous success in solving tasks depending on a single hyperparameter. When considering simultaneously a finite number of tasks, multi-task learning enables one to account for the similarities of the tasks via appropriate regularizers. A step further consists of learning a continuum of tasks for various loss functions. A promising approach, called \\emph{Parametric Task Learning}, has paved the way in the continuum setting for affine models and piecewise-linear loss functions. In this work, we introduce a novel approach called \\emph{Infinite Task Learning} whos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08809","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":""},"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":"1805.08809","created_at":"2026-05-18T00:03:36.850217+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08809v3","created_at":"2026-05-18T00:03:36.850217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08809","created_at":"2026-05-18T00:03:36.850217+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGSGLSUSSIGT","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGSGLSUSSIGT6PAJ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGSGLSUS","created_at":"2026-05-18T12:32:40.477152+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/NGSGLSUSSIGT6PAJNUUWBANKOO","json":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO.json","graph_json":"https://pith.science/api/pith-number/NGSGLSUSSIGT6PAJNUUWBANKOO/graph.json","events_json":"https://pith.science/api/pith-number/NGSGLSUSSIGT6PAJNUUWBANKOO/events.json","paper":"https://pith.science/paper/NGSGLSUS"},"agent_actions":{"view_html":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO","download_json":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO.json","view_paper":"https://pith.science/paper/NGSGLSUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08809&json=true","fetch_graph":"https://pith.science/api/pith-number/NGSGLSUSSIGT6PAJNUUWBANKOO/graph.json","fetch_events":"https://pith.science/api/pith-number/NGSGLSUSSIGT6PAJNUUWBANKOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO/action/storage_attestation","attest_author":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO/action/author_attestation","sign_citation":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO/action/citation_signature","submit_replication":"https://pith.science/pith/NGSGLSUSSIGT6PAJNUUWBANKOO/action/replication_record"}},"created_at":"2026-05-18T00:03:36.850217+00:00","updated_at":"2026-05-18T00:03:36.850217+00:00"}