{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WW6K5KHC36NQ547GC27HQ2UDEY","short_pith_number":"pith:WW6K5KHC","schema_version":"1.0","canonical_sha256":"b5bcaea8e2df9b0ef3e616be786a83261629e6277791f1c8ea9e1df4464417b3","source":{"kind":"arxiv","id":"2002.09543","version":1},"attestation_state":"computed","paper":{"title":"Modelling Latent Skills for Multitask Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Kris Cao","submitted_at":"2020-02-21T20:39:09Z","abstract_excerpt":"We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a task embedding space can help with both positive transfer across tasks and with efficient adaptation to new tasks. We instantiate this task embedding space as a latent variable in a latent variable sequence-to-sequence model. We evaluate this hypothesis by curating a series of monolingual text-to-text language generation datasets - covering a broad range of ta"},"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":"2002.09543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-21T20:39:09Z","cross_cats_sorted":[],"title_canon_sha256":"f2ae1c0b9c4c2b2b6ada65b8832a93de0c564dba4f7025d9e21ec726680d5e73","abstract_canon_sha256":"c3f0400a50b8f46155a7b626d9b2df5e72d2c3915e93c711fc098290a29a7b19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:08.814868Z","signature_b64":"CL9wPqODncdBl/dTgyIEUbm5SbOYmPLOnuaMMVGO4A/khSPM+y3JTlkAf8GURrN6w6vgSPxg6umYvhC3HMigCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5bcaea8e2df9b0ef3e616be786a83261629e6277791f1c8ea9e1df4464417b3","last_reissued_at":"2026-07-05T00:43:08.814490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:08.814490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modelling Latent Skills for Multitask Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Kris Cao","submitted_at":"2020-02-21T20:39:09Z","abstract_excerpt":"We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a task embedding space can help with both positive transfer across tasks and with efficient adaptation to new tasks. We instantiate this task embedding space as a latent variable in a latent variable sequence-to-sequence model. We evaluate this hypothesis by curating a series of monolingual text-to-text language generation datasets - covering a broad range of ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09543","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/2002.09543/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":"2002.09543","created_at":"2026-07-05T00:43:08.814548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09543v1","created_at":"2026-07-05T00:43:08.814548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09543","created_at":"2026-07-05T00:43:08.814548+00:00"},{"alias_kind":"pith_short_12","alias_value":"WW6K5KHC36NQ","created_at":"2026-07-05T00:43:08.814548+00:00"},{"alias_kind":"pith_short_16","alias_value":"WW6K5KHC36NQ547G","created_at":"2026-07-05T00:43:08.814548+00:00"},{"alias_kind":"pith_short_8","alias_value":"WW6K5KHC","created_at":"2026-07-05T00:43:08.814548+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/WW6K5KHC36NQ547GC27HQ2UDEY","json":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY.json","graph_json":"https://pith.science/api/pith-number/WW6K5KHC36NQ547GC27HQ2UDEY/graph.json","events_json":"https://pith.science/api/pith-number/WW6K5KHC36NQ547GC27HQ2UDEY/events.json","paper":"https://pith.science/paper/WW6K5KHC"},"agent_actions":{"view_html":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY","download_json":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY.json","view_paper":"https://pith.science/paper/WW6K5KHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09543&json=true","fetch_graph":"https://pith.science/api/pith-number/WW6K5KHC36NQ547GC27HQ2UDEY/graph.json","fetch_events":"https://pith.science/api/pith-number/WW6K5KHC36NQ547GC27HQ2UDEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY/action/storage_attestation","attest_author":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY/action/author_attestation","sign_citation":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY/action/citation_signature","submit_replication":"https://pith.science/pith/WW6K5KHC36NQ547GC27HQ2UDEY/action/replication_record"}},"created_at":"2026-07-05T00:43:08.814548+00:00","updated_at":"2026-07-05T00:43:08.814548+00:00"}