{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SO3EKQ7M4SHAMMOKXQC46N65ZX","short_pith_number":"pith:SO3EKQ7M","canonical_record":{"source":{"id":"2007.01126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T14:23:39Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"889f85f86572f81224c2807aa2e3a25741846d7ae7d926b0fffa12e3cefa8426","abstract_canon_sha256":"c05c7e047b00c7ad808c65ac9eb8f5765fb8a6b37432cc3c08699e16a950110e"},"schema_version":"1.0"},"canonical_sha256":"93b64543ece48e0631cabc05cf37ddcdc8ac5cbbd03cc657c103e3a857326fce","source":{"kind":"arxiv","id":"2007.01126","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01126","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01126v1","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01126","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"SO3EKQ7M4SHA","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"SO3EKQ7M4SHAMMOK","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"SO3EKQ7M","created_at":"2026-07-05T01:15:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SO3EKQ7M4SHAMMOKXQC46N65ZX","target":"record","payload":{"canonical_record":{"source":{"id":"2007.01126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T14:23:39Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"889f85f86572f81224c2807aa2e3a25741846d7ae7d926b0fffa12e3cefa8426","abstract_canon_sha256":"c05c7e047b00c7ad808c65ac9eb8f5765fb8a6b37432cc3c08699e16a950110e"},"schema_version":"1.0"},"canonical_sha256":"93b64543ece48e0631cabc05cf37ddcdc8ac5cbbd03cc657c103e3a857326fce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:51.984489Z","signature_b64":"NlLr3KhAC9Il6Z2htBg4LGzsBN+REgzL5uX+IiF4hX+gbbdzy68UZE0hmBbQk2GbgSrdKcIcz6M4KZHiWwfgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93b64543ece48e0631cabc05cf37ddcdc8ac5cbbd03cc657c103e3a857326fce","last_reissued_at":"2026-07-05T01:15:51.984092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:51.984092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.01126","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:15:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwCkmnEQjksg53Nt9zFyRSsosnKKAkJpCirfywYLNdeY27xOqP4KjnRzOKrSk2fH0dct88GNm97spn0Yw773DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:11:20.681022Z"},"content_sha256":"ec5abdb9c6393836a87173fefdc856b167438fe501fd5739e3234aa71e275bb0","schema_version":"1.0","event_id":"sha256:ec5abdb9c6393836a87173fefdc856b167438fe501fd5739e3234aa71e275bb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SO3EKQ7M4SHAMMOKXQC46N65ZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Brief Review of Deep Multi-task Learning and Auxiliary Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Farzad Khalvati, Khashayar Namdar, Partoo Vafaeikia","submitted_at":"2020-07-02T14:23:39Z","abstract_excerpt":"Multi-task learning (MTL) optimizes several learning tasks simultaneously and leverages their shared information to improve generalization and the prediction of the model for each task. Auxiliary tasks can be added to the main task to ultimately boost the performance. In this paper, we provide a brief review on the recent deep multi-task learning (dMTL) approaches followed by methods on selecting useful auxiliary tasks that can be used in dMTL to improve the performance of the model for the main task."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01126","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/2007.01126/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":"2026-07-05T01:15:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IlNW3QQuhqt0ARu4DWKwkIgddeaHWa0nbxnW5pVgKSu3G3ut6SAX4fjF7IwMtupQhTOMOjpMgTxYPj6nG6nkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:11:20.681373Z"},"content_sha256":"b42dcaa2fc4e3551390231e3e736eb093fb14851403cb20950ea898f09dcd217","schema_version":"1.0","event_id":"sha256:b42dcaa2fc4e3551390231e3e736eb093fb14851403cb20950ea898f09dcd217"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX/bundle.json","state_url":"https://pith.science/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX/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":"2026-08-20T11:11:20Z","links":{"resolver":"https://pith.science/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX","bundle":"https://pith.science/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX/bundle.json","state":"https://pith.science/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SO3EKQ7M4SHAMMOKXQC46N65ZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SO3EKQ7M4SHAMMOKXQC46N65ZX","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":"c05c7e047b00c7ad808c65ac9eb8f5765fb8a6b37432cc3c08699e16a950110e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T14:23:39Z","title_canon_sha256":"889f85f86572f81224c2807aa2e3a25741846d7ae7d926b0fffa12e3cefa8426"},"schema_version":"1.0","source":{"id":"2007.01126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01126","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01126v1","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01126","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"SO3EKQ7M4SHA","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"SO3EKQ7M4SHAMMOK","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"SO3EKQ7M","created_at":"2026-07-05T01:15:51Z"}],"graph_snapshots":[{"event_id":"sha256:b42dcaa2fc4e3551390231e3e736eb093fb14851403cb20950ea898f09dcd217","target":"graph","created_at":"2026-07-05T01:15:51Z","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/2007.01126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning (MTL) optimizes several learning tasks simultaneously and leverages their shared information to improve generalization and the prediction of the model for each task. Auxiliary tasks can be added to the main task to ultimately boost the performance. In this paper, we provide a brief review on the recent deep multi-task learning (dMTL) approaches followed by methods on selecting useful auxiliary tasks that can be used in dMTL to improve the performance of the model for the main task.","authors_text":"Farzad Khalvati, Khashayar Namdar, Partoo Vafaeikia","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T14:23:39Z","title":"A Brief Review of Deep Multi-task Learning and Auxiliary Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01126","kind":"arxiv","version":1},"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:ec5abdb9c6393836a87173fefdc856b167438fe501fd5739e3234aa71e275bb0","target":"record","created_at":"2026-07-05T01:15:51Z","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":"c05c7e047b00c7ad808c65ac9eb8f5765fb8a6b37432cc3c08699e16a950110e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T14:23:39Z","title_canon_sha256":"889f85f86572f81224c2807aa2e3a25741846d7ae7d926b0fffa12e3cefa8426"},"schema_version":"1.0","source":{"id":"2007.01126","kind":"arxiv","version":1}},"canonical_sha256":"93b64543ece48e0631cabc05cf37ddcdc8ac5cbbd03cc657c103e3a857326fce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93b64543ece48e0631cabc05cf37ddcdc8ac5cbbd03cc657c103e3a857326fce","first_computed_at":"2026-07-05T01:15:51.984092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:51.984092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NlLr3KhAC9Il6Z2htBg4LGzsBN+REgzL5uX+IiF4hX+gbbdzy68UZE0hmBbQk2GbgSrdKcIcz6M4KZHiWwfgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:51.984489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.01126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec5abdb9c6393836a87173fefdc856b167438fe501fd5739e3234aa71e275bb0","sha256:b42dcaa2fc4e3551390231e3e736eb093fb14851403cb20950ea898f09dcd217"],"state_sha256":"45ad83500eabc13196935ae396b135e9bc733be1b1c528eb2def9e6c2104caf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K3p/6vOZCIDEeyiBB04jbnOfj4QFy6QFZ7xZFGIlV7pga/mLXi0uo8UmSZWDWWaUPvi37lS0kjpNlp5FozRBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T11:11:20.684534Z","bundle_sha256":"56f6b82ae872e5b9325bb37d352d6aaaa170f23714bd7902c035b841132ea9f5"}}