{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4U3K4IWINIAQ4TERVOKB3R2WBD","short_pith_number":"pith:4U3K4IWI","schema_version":"1.0","canonical_sha256":"e536ae22c86a010e4c91ab941dc75608d36e45ee51919b862cbccd65b459e818","source":{"kind":"arxiv","id":"2006.01895","version":2},"attestation_state":"computed","paper":{"title":"Learning to Branch for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Lee, Daniel Ulbricht, Pengsheng Guo","submitted_at":"2020-06-02T19:23:21Z","abstract_excerpt":"Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of a network. However, over-sharing a network could erroneously enforce over-generalization, causing negative knowledge transfer across tasks. Prior works rely on human intuition or pre-computed task relatedness scores for ad hoc branching structures. They provide sub-optimal end results and often require huge efforts for the trial-and-error process. In this work, we present an automated multi-task learning algorithm that "},"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":"2006.01895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-02T19:23:21Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"ee278415fffca6afabfbc99a187bb00ea44718c7e1f96dfdb002334e2b3d0538","abstract_canon_sha256":"28b93fa91734a53e355f4c8cef79bf7c72171e9598eccc3e6beea51531693b82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:07.293156Z","signature_b64":"cW3e3BZM5mfRO5VlOdR9h7yTkEEXZlUnoMkmCaHRdhS4Izhu7znp9JoqEx0jU2UbZMFBTSiW0PVWdiCFIweMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e536ae22c86a010e4c91ab941dc75608d36e45ee51919b862cbccd65b459e818","last_reissued_at":"2026-07-05T01:09:07.292731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:07.292731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Branch for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Lee, Daniel Ulbricht, Pengsheng Guo","submitted_at":"2020-06-02T19:23:21Z","abstract_excerpt":"Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of a network. However, over-sharing a network could erroneously enforce over-generalization, causing negative knowledge transfer across tasks. Prior works rely on human intuition or pre-computed task relatedness scores for ad hoc branching structures. They provide sub-optimal end results and often require huge efforts for the trial-and-error process. In this work, we present an automated multi-task learning algorithm that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01895","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/2006.01895/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":"2006.01895","created_at":"2026-07-05T01:09:07.292798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.01895v2","created_at":"2026-07-05T01:09:07.292798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01895","created_at":"2026-07-05T01:09:07.292798+00:00"},{"alias_kind":"pith_short_12","alias_value":"4U3K4IWINIAQ","created_at":"2026-07-05T01:09:07.292798+00:00"},{"alias_kind":"pith_short_16","alias_value":"4U3K4IWINIAQ4TER","created_at":"2026-07-05T01:09:07.292798+00:00"},{"alias_kind":"pith_short_8","alias_value":"4U3K4IWI","created_at":"2026-07-05T01:09:07.292798+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/4U3K4IWINIAQ4TERVOKB3R2WBD","json":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD.json","graph_json":"https://pith.science/api/pith-number/4U3K4IWINIAQ4TERVOKB3R2WBD/graph.json","events_json":"https://pith.science/api/pith-number/4U3K4IWINIAQ4TERVOKB3R2WBD/events.json","paper":"https://pith.science/paper/4U3K4IWI"},"agent_actions":{"view_html":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD","download_json":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD.json","view_paper":"https://pith.science/paper/4U3K4IWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.01895&json=true","fetch_graph":"https://pith.science/api/pith-number/4U3K4IWINIAQ4TERVOKB3R2WBD/graph.json","fetch_events":"https://pith.science/api/pith-number/4U3K4IWINIAQ4TERVOKB3R2WBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD/action/storage_attestation","attest_author":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD/action/author_attestation","sign_citation":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD/action/citation_signature","submit_replication":"https://pith.science/pith/4U3K4IWINIAQ4TERVOKB3R2WBD/action/replication_record"}},"created_at":"2026-07-05T01:09:07.292798+00:00","updated_at":"2026-07-05T01:09:07.292798+00:00"}