{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WO4KB3IG7DPSEGRZ4YP5Q7AMJF","short_pith_number":"pith:WO4KB3IG","schema_version":"1.0","canonical_sha256":"b3b8a0ed06f8df221a39e61fd87c0c495a9e0bc842948a4d6259935487ec8433","source":{"kind":"arxiv","id":"2606.19521","version":1},"attestation_state":"computed","paper":{"title":"Interactive Pareto navigation for deep multi-task learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Augustina C. Amakor, Konstantin Sonntag, Sebastian Peitz","submitted_at":"2026-06-17T19:08:37Z","abstract_excerpt":"In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity to choose appropriate trade-offs. A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum. This often fails to capture either the decision maker's preferences as a result of the shape of the Pareto front, or requires multiple adjustments and computations which becomes prohibitively expensive in deep learning applications. To address these issues, we introduce a nov"},"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":"2606.19521","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T19:08:37Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"03af07849768c7de7b7a36de8babccc0c6355b5c916ed13c285cbc2f294288d2","abstract_canon_sha256":"d1c03b19c169e3fc006bfa2e7549abdd05e3699decaa86144c7443f54e35b256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:27.689292Z","signature_b64":"cd62/U7BxAt8t+gMM1zA7dv0zmYE/ViHgqfi0rUwIAHVHWPdJD1ylt/4CvKJ8vPBE+oUjovcpeWcT229oZjlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3b8a0ed06f8df221a39e61fd87c0c495a9e0bc842948a4d6259935487ec8433","last_reissued_at":"2026-06-19T16:12:27.688947Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:27.688947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Pareto navigation for deep multi-task learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Augustina C. Amakor, Konstantin Sonntag, Sebastian Peitz","submitted_at":"2026-06-17T19:08:37Z","abstract_excerpt":"In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity to choose appropriate trade-offs. A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum. This often fails to capture either the decision maker's preferences as a result of the shape of the Pareto front, or requires multiple adjustments and computations which becomes prohibitively expensive in deep learning applications. To address these issues, we introduce a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19521","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/2606.19521/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":"2606.19521","created_at":"2026-06-19T16:12:27.689009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19521v1","created_at":"2026-06-19T16:12:27.689009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19521","created_at":"2026-06-19T16:12:27.689009+00:00"},{"alias_kind":"pith_short_12","alias_value":"WO4KB3IG7DPS","created_at":"2026-06-19T16:12:27.689009+00:00"},{"alias_kind":"pith_short_16","alias_value":"WO4KB3IG7DPSEGRZ","created_at":"2026-06-19T16:12:27.689009+00:00"},{"alias_kind":"pith_short_8","alias_value":"WO4KB3IG","created_at":"2026-06-19T16:12:27.689009+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/WO4KB3IG7DPSEGRZ4YP5Q7AMJF","json":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF.json","graph_json":"https://pith.science/api/pith-number/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/graph.json","events_json":"https://pith.science/api/pith-number/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/events.json","paper":"https://pith.science/paper/WO4KB3IG"},"agent_actions":{"view_html":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF","download_json":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF.json","view_paper":"https://pith.science/paper/WO4KB3IG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19521&json=true","fetch_graph":"https://pith.science/api/pith-number/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/graph.json","fetch_events":"https://pith.science/api/pith-number/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/action/storage_attestation","attest_author":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/action/author_attestation","sign_citation":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/action/citation_signature","submit_replication":"https://pith.science/pith/WO4KB3IG7DPSEGRZ4YP5Q7AMJF/action/replication_record"}},"created_at":"2026-06-19T16:12:27.689009+00:00","updated_at":"2026-06-19T16:12:27.689009+00:00"}