{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RRKA2MVZCCKL4FWZWFPKTQIUYK","short_pith_number":"pith:RRKA2MVZ","canonical_record":{"source":{"id":"2106.10595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-20T01:30:37Z","cross_cats_sorted":[],"title_canon_sha256":"d50f8c11e1588f2d45cba0845f20b29a8a9d5fb173eb5d9b87b230fcf65ddfea","abstract_canon_sha256":"1b59f7930c8b78983bc8a03c9fc9f53d988003ee88c6e5b5b45154505c6cc03e"},"schema_version":"1.0"},"canonical_sha256":"8c540d32b91094be16d9b15ea9c114c2ab6768415749e2c843e072a9f2ff13f5","source":{"kind":"arxiv","id":"2106.10595","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10595","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10595v3","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10595","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"pith_short_12","alias_value":"RRKA2MVZCCKL","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"RRKA2MVZCCKL4FWZ","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"RRKA2MVZ","created_at":"2026-07-05T04:27:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RRKA2MVZCCKL4FWZWFPKTQIUYK","target":"record","payload":{"canonical_record":{"source":{"id":"2106.10595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-20T01:30:37Z","cross_cats_sorted":[],"title_canon_sha256":"d50f8c11e1588f2d45cba0845f20b29a8a9d5fb173eb5d9b87b230fcf65ddfea","abstract_canon_sha256":"1b59f7930c8b78983bc8a03c9fc9f53d988003ee88c6e5b5b45154505c6cc03e"},"schema_version":"1.0"},"canonical_sha256":"8c540d32b91094be16d9b15ea9c114c2ab6768415749e2c843e072a9f2ff13f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:06.132524Z","signature_b64":"AqoTwkkFJCx0hRgjiQt0+iynDZorVdw2HtoIdIdOr2r6xvWDQIpIABwinDB1P9R+TlrORUQo4nyieL1O3nA0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c540d32b91094be16d9b15ea9c114c2ab6768415749e2c843e072a9f2ff13f5","last_reissued_at":"2026-07-05T04:27:06.132041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:06.132041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.10595","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:27:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbXaaUEtzX+c9l3hpaYLm7+D435CDuixTqeN4kWTGH2yUBYqGx6DaHHyY6Nxq8Gu9oNXKH7DYAZhH8YYXpLlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:42:47.850217Z"},"content_sha256":"fcdb14f83d54ed9aee27614543b3cace6459d35814c1382d48dab97fb5935206","schema_version":"1.0","event_id":"sha256:fcdb14f83d54ed9aee27614543b3cace6459d35814c1382d48dab97fb5935206"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RRKA2MVZCCKL4FWZWFPKTQIUYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heterogeneous Multi-task Learning with Expert Diversity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frederick Tung, Gabriel L. Oliveira, Raquel Aoki","submitted_at":"2021-06-20T01:30:37Z","abstract_excerpt":"Predicting multiple heterogeneous biological and medical targets is a challenge for traditional deep learning models. In contrast to single-task learning, in which a separate model is trained for each target, multi-task learning (MTL) optimizes a single model to predict multiple related targets simultaneously. To address this challenge, we propose the Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx). Our work aims to tackle the heterogeneous MTL setting, in which the same model optimizes multiple tasks with different characteristics. Such a scenario can overwhelm current MTL approaches "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10595","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.10595/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:27:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYow5XqQhKbN+UiqjtiMnN0QQQJV4LtQj/8i2YlGb+UIWCAVF7t96uDNz5O08ygL7CUjSG+g0pKdy2rtOMpLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:42:47.850617Z"},"content_sha256":"7386f48d95f22ba411e32d4a75dc5fcfdc9aff5bb0818ee860d52863ffab2c7b","schema_version":"1.0","event_id":"sha256:7386f48d95f22ba411e32d4a75dc5fcfdc9aff5bb0818ee860d52863ffab2c7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK/bundle.json","state_url":"https://pith.science/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T10:42:47Z","links":{"resolver":"https://pith.science/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK","bundle":"https://pith.science/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK/bundle.json","state":"https://pith.science/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRKA2MVZCCKL4FWZWFPKTQIUYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RRKA2MVZCCKL4FWZWFPKTQIUYK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1b59f7930c8b78983bc8a03c9fc9f53d988003ee88c6e5b5b45154505c6cc03e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-20T01:30:37Z","title_canon_sha256":"d50f8c11e1588f2d45cba0845f20b29a8a9d5fb173eb5d9b87b230fcf65ddfea"},"schema_version":"1.0","source":{"id":"2106.10595","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10595","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10595v3","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10595","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"pith_short_12","alias_value":"RRKA2MVZCCKL","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"pith_short_16","alias_value":"RRKA2MVZCCKL4FWZ","created_at":"2026-07-05T04:27:06Z"},{"alias_kind":"pith_short_8","alias_value":"RRKA2MVZ","created_at":"2026-07-05T04:27:06Z"}],"graph_snapshots":[{"event_id":"sha256:7386f48d95f22ba411e32d4a75dc5fcfdc9aff5bb0818ee860d52863ffab2c7b","target":"graph","created_at":"2026-07-05T04:27:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.10595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predicting multiple heterogeneous biological and medical targets is a challenge for traditional deep learning models. In contrast to single-task learning, in which a separate model is trained for each target, multi-task learning (MTL) optimizes a single model to predict multiple related targets simultaneously. To address this challenge, we propose the Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx). Our work aims to tackle the heterogeneous MTL setting, in which the same model optimizes multiple tasks with different characteristics. Such a scenario can overwhelm current MTL approaches ","authors_text":"Frederick Tung, Gabriel L. Oliveira, Raquel Aoki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-20T01:30:37Z","title":"Heterogeneous Multi-task Learning with Expert Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10595","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fcdb14f83d54ed9aee27614543b3cace6459d35814c1382d48dab97fb5935206","target":"record","created_at":"2026-07-05T04:27:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1b59f7930c8b78983bc8a03c9fc9f53d988003ee88c6e5b5b45154505c6cc03e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-20T01:30:37Z","title_canon_sha256":"d50f8c11e1588f2d45cba0845f20b29a8a9d5fb173eb5d9b87b230fcf65ddfea"},"schema_version":"1.0","source":{"id":"2106.10595","kind":"arxiv","version":3}},"canonical_sha256":"8c540d32b91094be16d9b15ea9c114c2ab6768415749e2c843e072a9f2ff13f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c540d32b91094be16d9b15ea9c114c2ab6768415749e2c843e072a9f2ff13f5","first_computed_at":"2026-07-05T04:27:06.132041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:06.132041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqoTwkkFJCx0hRgjiQt0+iynDZorVdw2HtoIdIdOr2r6xvWDQIpIABwinDB1P9R+TlrORUQo4nyieL1O3nA0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:06.132524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.10595","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcdb14f83d54ed9aee27614543b3cace6459d35814c1382d48dab97fb5935206","sha256:7386f48d95f22ba411e32d4a75dc5fcfdc9aff5bb0818ee860d52863ffab2c7b"],"state_sha256":"dd4882a5fb8e0fc189c5c0ebbba125e18482de976bd3f42f7aa34a4f64064f10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5/te6PP9YBHSen3AW0GsBFmnM814dHIGaO9enXeq2y1WseXKDnFNKXJFRv5jAA35uhoIykQt9TGFLti7rbDoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:42:47.852644Z","bundle_sha256":"78659925b030a74a9b6563ca2c57475d7d52b2e42b2ca9d4d14e3ae7244daf46"}}