{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GSAWU3F6DXRACEZWLJ6T23ZUNQ","short_pith_number":"pith:GSAWU3F6","schema_version":"1.0","canonical_sha256":"34816a6cbe1de20113365a7d3d6f346c02623a6d103f6c4a6dd68dfdabe119f5","source":{"kind":"arxiv","id":"2003.02455","version":3},"attestation_state":"computed","paper":{"title":"PAC-Bayes meta-learning with implicit task-specific posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Gustavo Carneiro, Thanh-Toan Do","submitted_at":"2020-03-05T06:56:19Z","abstract_excerpt":"We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single task setting to the meta-learning multiple task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-lear"},"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":"2003.02455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-05T06:56:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"df741bb170a20cee532014c2ccc8f903f705e612af4ed24dee61ab206de131c9","abstract_canon_sha256":"e6820eb447d798556a6901e5c2b33e3875359a157e6328246edaa74f78954617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:25.110979Z","signature_b64":"IZ5D04YFX0oZvHDOBCR74TKYuobjoFns59oViUzUt7TT0fhNarzhxtVPwobzjwJjjlmpSIlPXs1z2VGbqwOpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34816a6cbe1de20113365a7d3d6f346c02623a6d103f6c4a6dd68dfdabe119f5","last_reissued_at":"2026-07-05T03:27:25.110562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:25.110562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC-Bayes meta-learning with implicit task-specific posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Gustavo Carneiro, Thanh-Toan Do","submitted_at":"2020-03-05T06:56:19Z","abstract_excerpt":"We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single task setting to the meta-learning multiple task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02455","kind":"arxiv","version":3},"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/2003.02455/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":"2003.02455","created_at":"2026-07-05T03:27:25.110620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.02455v3","created_at":"2026-07-05T03:27:25.110620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02455","created_at":"2026-07-05T03:27:25.110620+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSAWU3F6DXRA","created_at":"2026-07-05T03:27:25.110620+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSAWU3F6DXRACEZW","created_at":"2026-07-05T03:27:25.110620+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSAWU3F6","created_at":"2026-07-05T03:27:25.110620+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/GSAWU3F6DXRACEZWLJ6T23ZUNQ","json":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ.json","graph_json":"https://pith.science/api/pith-number/GSAWU3F6DXRACEZWLJ6T23ZUNQ/graph.json","events_json":"https://pith.science/api/pith-number/GSAWU3F6DXRACEZWLJ6T23ZUNQ/events.json","paper":"https://pith.science/paper/GSAWU3F6"},"agent_actions":{"view_html":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ","download_json":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ.json","view_paper":"https://pith.science/paper/GSAWU3F6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.02455&json=true","fetch_graph":"https://pith.science/api/pith-number/GSAWU3F6DXRACEZWLJ6T23ZUNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GSAWU3F6DXRACEZWLJ6T23ZUNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ/action/storage_attestation","attest_author":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ/action/author_attestation","sign_citation":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ/action/citation_signature","submit_replication":"https://pith.science/pith/GSAWU3F6DXRACEZWLJ6T23ZUNQ/action/replication_record"}},"created_at":"2026-07-05T03:27:25.110620+00:00","updated_at":"2026-07-05T03:27:25.110620+00:00"}