{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GPMSASKTXQMNO4O7UO7JDZVXJP","short_pith_number":"pith:GPMSASKT","schema_version":"1.0","canonical_sha256":"33d9204953bc18d771dfa3be91e6b74bcb291dc6cf9688c85e6609ca6eecd441","source":{"kind":"arxiv","id":"2202.03091","version":2},"attestation_state":"computed","paper":{"title":"Auto-Lambda: Disentangling Dynamic Task Relationships","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew J. Davison, Edward Johns, Shikun Liu, Stephen James","submitted_at":"2022-02-07T12:07:50Z","abstract_excerpt":"Understanding the structure of multiple related tasks allows for multi-task learning to improve the generalisation ability of one or all of them. However, it usually requires training each pairwise combination of tasks together in order to capture task relationships, at an extremely high computational cost. In this work, we learn task relationships via an automated weighting framework, named Auto-Lambda. Unlike previous methods where task relationships are assumed to be fixed, Auto-Lambda is a gradient-based meta learning framework which explores continuous, dynamic task relationships via task"},"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":"2202.03091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T12:07:50Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"b5e8071741edd61aadd680cc5141f24662bc5ec9e058847c8934b3cece804526","abstract_canon_sha256":"e9f255de497288745afda342a588089e194f5fa52ca39c8c92f426a73b3c804b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:30.671985Z","signature_b64":"ZkD5jEdJsfV/d60M3bhLQJ0tCtADHvjIW9Xzqz93oeTiKK50Suqb7AtQcUkcSP2obWdU9S2tBrYztE1eXAjXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33d9204953bc18d771dfa3be91e6b74bcb291dc6cf9688c85e6609ca6eecd441","last_reissued_at":"2026-07-05T04:28:30.671453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:30.671453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-Lambda: Disentangling Dynamic Task Relationships","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew J. Davison, Edward Johns, Shikun Liu, Stephen James","submitted_at":"2022-02-07T12:07:50Z","abstract_excerpt":"Understanding the structure of multiple related tasks allows for multi-task learning to improve the generalisation ability of one or all of them. However, it usually requires training each pairwise combination of tasks together in order to capture task relationships, at an extremely high computational cost. In this work, we learn task relationships via an automated weighting framework, named Auto-Lambda. Unlike previous methods where task relationships are assumed to be fixed, Auto-Lambda is a gradient-based meta learning framework which explores continuous, dynamic task relationships via task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03091","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/2202.03091/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":"2202.03091","created_at":"2026-07-05T04:28:30.671513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03091v2","created_at":"2026-07-05T04:28:30.671513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03091","created_at":"2026-07-05T04:28:30.671513+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPMSASKTXQMN","created_at":"2026-07-05T04:28:30.671513+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPMSASKTXQMNO4O7","created_at":"2026-07-05T04:28:30.671513+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPMSASKT","created_at":"2026-07-05T04:28:30.671513+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/GPMSASKTXQMNO4O7UO7JDZVXJP","json":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP.json","graph_json":"https://pith.science/api/pith-number/GPMSASKTXQMNO4O7UO7JDZVXJP/graph.json","events_json":"https://pith.science/api/pith-number/GPMSASKTXQMNO4O7UO7JDZVXJP/events.json","paper":"https://pith.science/paper/GPMSASKT"},"agent_actions":{"view_html":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP","download_json":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP.json","view_paper":"https://pith.science/paper/GPMSASKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03091&json=true","fetch_graph":"https://pith.science/api/pith-number/GPMSASKTXQMNO4O7UO7JDZVXJP/graph.json","fetch_events":"https://pith.science/api/pith-number/GPMSASKTXQMNO4O7UO7JDZVXJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP/action/storage_attestation","attest_author":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP/action/author_attestation","sign_citation":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP/action/citation_signature","submit_replication":"https://pith.science/pith/GPMSASKTXQMNO4O7UO7JDZVXJP/action/replication_record"}},"created_at":"2026-07-05T04:28:30.671513+00:00","updated_at":"2026-07-05T04:28:30.671513+00:00"}