{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EO5WWOYADZ4ZIPZBVL2FW2YHRK","short_pith_number":"pith:EO5WWOYA","schema_version":"1.0","canonical_sha256":"23bb6b3b001e79943f21aaf45b6b078aac306f540b4a6ca3bbdcf56daefaab83","source":{"kind":"arxiv","id":"2111.05820","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Neural Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiayi Shen, Ling Shao, Marcel Worring, Xiantong Zhen","submitted_at":"2021-11-10T17:27:46Z","abstract_excerpt":"Neural processes have recently emerged as a class of powerful neural latent variable models that combine the strengths of neural networks and stochastic processes. As they can encode contextual data in the network's function space, they offer a new way to model task relatedness in multi-task learning. To study its potential, we develop multi-task neural processes, a new variant of neural processes for multi-task learning. In particular, we propose to explore transferable knowledge from related tasks in the function space to provide inductive bias for improving each individual task. To do so, w"},"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":"2111.05820","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T17:27:46Z","cross_cats_sorted":[],"title_canon_sha256":"31e50db6cdd1c052e83c7a42939a7c8d33c6abfd6d932e73ded493be50b52acd","abstract_canon_sha256":"c1f1808ea13dafcce911854c7209f938c91177d8d963f695832348a89a5c0f74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:58.433842Z","signature_b64":"gWItVsOAIyCYqbhGBZhra5ktAbnDdjmiAv4S2qqpNJu9LEHfkjf2ILjXtT16UwMzaWTaPqQhNOMwUuLYLIN5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23bb6b3b001e79943f21aaf45b6b078aac306f540b4a6ca3bbdcf56daefaab83","last_reissued_at":"2026-07-05T03:36:58.433448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:58.433448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Neural Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiayi Shen, Ling Shao, Marcel Worring, Xiantong Zhen","submitted_at":"2021-11-10T17:27:46Z","abstract_excerpt":"Neural processes have recently emerged as a class of powerful neural latent variable models that combine the strengths of neural networks and stochastic processes. As they can encode contextual data in the network's function space, they offer a new way to model task relatedness in multi-task learning. To study its potential, we develop multi-task neural processes, a new variant of neural processes for multi-task learning. In particular, we propose to explore transferable knowledge from related tasks in the function space to provide inductive bias for improving each individual task. To do so, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05820","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/2111.05820/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":"2111.05820","created_at":"2026-07-05T03:36:58.433506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05820v2","created_at":"2026-07-05T03:36:58.433506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05820","created_at":"2026-07-05T03:36:58.433506+00:00"},{"alias_kind":"pith_short_12","alias_value":"EO5WWOYADZ4Z","created_at":"2026-07-05T03:36:58.433506+00:00"},{"alias_kind":"pith_short_16","alias_value":"EO5WWOYADZ4ZIPZB","created_at":"2026-07-05T03:36:58.433506+00:00"},{"alias_kind":"pith_short_8","alias_value":"EO5WWOYA","created_at":"2026-07-05T03:36:58.433506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01726","citing_title":"Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK","json":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK.json","graph_json":"https://pith.science/api/pith-number/EO5WWOYADZ4ZIPZBVL2FW2YHRK/graph.json","events_json":"https://pith.science/api/pith-number/EO5WWOYADZ4ZIPZBVL2FW2YHRK/events.json","paper":"https://pith.science/paper/EO5WWOYA"},"agent_actions":{"view_html":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK","download_json":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK.json","view_paper":"https://pith.science/paper/EO5WWOYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05820&json=true","fetch_graph":"https://pith.science/api/pith-number/EO5WWOYADZ4ZIPZBVL2FW2YHRK/graph.json","fetch_events":"https://pith.science/api/pith-number/EO5WWOYADZ4ZIPZBVL2FW2YHRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK/action/storage_attestation","attest_author":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK/action/author_attestation","sign_citation":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK/action/citation_signature","submit_replication":"https://pith.science/pith/EO5WWOYADZ4ZIPZBVL2FW2YHRK/action/replication_record"}},"created_at":"2026-07-05T03:36:58.433506+00:00","updated_at":"2026-07-05T03:36:58.433506+00:00"}