{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IKCDII7QJ76TC55UFPPHQ2NCQP","short_pith_number":"pith:IKCDII7Q","schema_version":"1.0","canonical_sha256":"42843423f04ffd3177b42bde7869a283f538e8d58dad719369195510add83bd5","source":{"kind":"arxiv","id":"2307.12519","version":1},"attestation_state":"computed","paper":{"title":"DEPHN: Different Expression Parallel Heterogeneous Network using virtual gradient optimization for Multi-task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Menglin Kong, Muzhou Hou, Ri Su, Shaojie Zhao","submitted_at":"2023-07-24T04:29:00Z","abstract_excerpt":"Recommendation system algorithm based on multi-task learning (MTL) is the major method for Internet operators to understand users and predict their behaviors in the multi-behavior scenario of platform. Task correlation is an important consideration of MTL goals, traditional models use shared-bottom models and gating experts to realize shared representation learning and information differentiation. However, The relationship between real-world tasks is often more complex than existing methods do not handle properly sharing information. In this paper, we propose an Different Expression Parallel H"},"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":"2307.12519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-24T04:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"82eeb186ebcb9437e4a097b94ef0eeafc7a9589dc3ba8c0a20c7172f6a560b1d","abstract_canon_sha256":"1095f418736ff50e25712ca6d849f2ce037a28dd8daaf9c700d29df224c9037f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:55.100651Z","signature_b64":"JrvTgmo0IXcxV5c1CQCmq8zRwJLyS0IRoRheGgOu2o+a7QYVcev2nN/GCZbFa90+ALfrA6kB8NpKJDQt+ugJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42843423f04ffd3177b42bde7869a283f538e8d58dad719369195510add83bd5","last_reissued_at":"2026-07-05T06:33:55.100177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:55.100177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEPHN: Different Expression Parallel Heterogeneous Network using virtual gradient optimization for Multi-task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Menglin Kong, Muzhou Hou, Ri Su, Shaojie Zhao","submitted_at":"2023-07-24T04:29:00Z","abstract_excerpt":"Recommendation system algorithm based on multi-task learning (MTL) is the major method for Internet operators to understand users and predict their behaviors in the multi-behavior scenario of platform. Task correlation is an important consideration of MTL goals, traditional models use shared-bottom models and gating experts to realize shared representation learning and information differentiation. However, The relationship between real-world tasks is often more complex than existing methods do not handle properly sharing information. In this paper, we propose an Different Expression Parallel H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12519","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/2307.12519/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":"2307.12519","created_at":"2026-07-05T06:33:55.100235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12519v1","created_at":"2026-07-05T06:33:55.100235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12519","created_at":"2026-07-05T06:33:55.100235+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKCDII7QJ76T","created_at":"2026-07-05T06:33:55.100235+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKCDII7QJ76TC55U","created_at":"2026-07-05T06:33:55.100235+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKCDII7Q","created_at":"2026-07-05T06:33:55.100235+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/IKCDII7QJ76TC55UFPPHQ2NCQP","json":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP.json","graph_json":"https://pith.science/api/pith-number/IKCDII7QJ76TC55UFPPHQ2NCQP/graph.json","events_json":"https://pith.science/api/pith-number/IKCDII7QJ76TC55UFPPHQ2NCQP/events.json","paper":"https://pith.science/paper/IKCDII7Q"},"agent_actions":{"view_html":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP","download_json":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP.json","view_paper":"https://pith.science/paper/IKCDII7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12519&json=true","fetch_graph":"https://pith.science/api/pith-number/IKCDII7QJ76TC55UFPPHQ2NCQP/graph.json","fetch_events":"https://pith.science/api/pith-number/IKCDII7QJ76TC55UFPPHQ2NCQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP/action/storage_attestation","attest_author":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP/action/author_attestation","sign_citation":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP/action/citation_signature","submit_replication":"https://pith.science/pith/IKCDII7QJ76TC55UFPPHQ2NCQP/action/replication_record"}},"created_at":"2026-07-05T06:33:55.100235+00:00","updated_at":"2026-07-05T06:33:55.100235+00:00"}