{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UP7AVC7RFDR5S2TWCTHERZUNUA","short_pith_number":"pith:UP7AVC7R","schema_version":"1.0","canonical_sha256":"a3fe0a8bf128e3d96a7614ce48e68da0366c6846085544e3a93876d9df0b9614","source":{"kind":"arxiv","id":"2111.14122","version":1},"attestation_state":"computed","paper":{"title":"Cross-Task Consistency Learning Framework for Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akihiro Nakano, Kazuyuki Demachi, Shi Chen","submitted_at":"2021-11-28T11:55:19Z","abstract_excerpt":"Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features between tasks and enhance predictions compared to when learning each task independently. We propose a new learning framework for 2-task MTL problem that uses the predictions of one task as inputs to another network to predict the other task. We define two new loss terms inspired by cycle-consistency loss and contrastive learning, alignment loss and cross-task c"},"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":"2111.14122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-28T11:55:19Z","cross_cats_sorted":[],"title_canon_sha256":"ae51b7c0e559e341fcf1545a89925672d5b1ff3b9c54c279efbd9a840703ceec","abstract_canon_sha256":"f1a4cb1d91774c0014aea0fa29827d6468617b0a209db4c6ef45cb85daaf153a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:39.484128Z","signature_b64":"01BMO5ROmQL3TZQNoQqpoT6lMb8Wtg9GWO8skrOaaVxJO6Mm61yl9p6gnL0MBqBFbExoV6BodiCeZUsrQaBQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3fe0a8bf128e3d96a7614ce48e68da0366c6846085544e3a93876d9df0b9614","last_reissued_at":"2026-07-05T03:35:39.483714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:39.483714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Task Consistency Learning Framework for Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akihiro Nakano, Kazuyuki Demachi, Shi Chen","submitted_at":"2021-11-28T11:55:19Z","abstract_excerpt":"Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features between tasks and enhance predictions compared to when learning each task independently. We propose a new learning framework for 2-task MTL problem that uses the predictions of one task as inputs to another network to predict the other task. We define two new loss terms inspired by cycle-consistency loss and contrastive learning, alignment loss and cross-task c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14122","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/2111.14122/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":"2111.14122","created_at":"2026-07-05T03:35:39.483764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.14122v1","created_at":"2026-07-05T03:35:39.483764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14122","created_at":"2026-07-05T03:35:39.483764+00:00"},{"alias_kind":"pith_short_12","alias_value":"UP7AVC7RFDR5","created_at":"2026-07-05T03:35:39.483764+00:00"},{"alias_kind":"pith_short_16","alias_value":"UP7AVC7RFDR5S2TW","created_at":"2026-07-05T03:35:39.483764+00:00"},{"alias_kind":"pith_short_8","alias_value":"UP7AVC7R","created_at":"2026-07-05T03:35:39.483764+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/UP7AVC7RFDR5S2TWCTHERZUNUA","json":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA.json","graph_json":"https://pith.science/api/pith-number/UP7AVC7RFDR5S2TWCTHERZUNUA/graph.json","events_json":"https://pith.science/api/pith-number/UP7AVC7RFDR5S2TWCTHERZUNUA/events.json","paper":"https://pith.science/paper/UP7AVC7R"},"agent_actions":{"view_html":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA","download_json":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA.json","view_paper":"https://pith.science/paper/UP7AVC7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.14122&json=true","fetch_graph":"https://pith.science/api/pith-number/UP7AVC7RFDR5S2TWCTHERZUNUA/graph.json","fetch_events":"https://pith.science/api/pith-number/UP7AVC7RFDR5S2TWCTHERZUNUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA/action/storage_attestation","attest_author":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA/action/author_attestation","sign_citation":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA/action/citation_signature","submit_replication":"https://pith.science/pith/UP7AVC7RFDR5S2TWCTHERZUNUA/action/replication_record"}},"created_at":"2026-07-05T03:35:39.483764+00:00","updated_at":"2026-07-05T03:35:39.483764+00:00"}