{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DWP63CKBSVLIWL2NGT3CPFRRB4","short_pith_number":"pith:DWP63CKB","schema_version":"1.0","canonical_sha256":"1d9fed894195568b2f4d34f62796310f06fcbfc2033d908d3359b359e9f0d32a","source":{"kind":"arxiv","id":"2205.15745","version":3},"attestation_state":"computed","paper":{"title":"HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"J. Tabor, M. Przewi\\k{e}\\'zlikowski, M. Zi\\k{e}ba, P. Przybysz, P. Spurek","submitted_at":"2022-05-31T12:31:21Z","abstract_excerpt":"The aim of Few-Shot learning methods is to train models which can easily adapt to previously unseen tasks, based on small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic Meta-Learning (MAML). The main idea behind this method is to learn the general weights of the meta-model, which are further adapted to specific problems in a small number of gradient steps. However, the model's main limitation lies in the fact that the update procedure is realized by gradient-based optimisation. In consequence, MAML cannot always modify weights to the essenti"},"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":"2205.15745","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:31:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1b75ec36a3da2324c505d00a0c638a0ec11881b2d9896ae31d995b3a3ece609","abstract_canon_sha256":"48ef6b344669a7d5c6cabe2186278e4fe44b1874fe6e7a85925529e37c4d4132"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:51.037444Z","signature_b64":"wu8agVJFUsL/SlZZ05CFNQXg/Ct4HeC2XInoVSbOyarz/u0TzHFHRwBRtwgVZX48QiHMKW+YjwztHB0HKb3wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d9fed894195568b2f4d34f62796310f06fcbfc2033d908d3359b359e9f0d32a","last_reissued_at":"2026-07-05T08:40:51.036973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:51.036973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"J. Tabor, M. Przewi\\k{e}\\'zlikowski, M. Zi\\k{e}ba, P. Przybysz, P. Spurek","submitted_at":"2022-05-31T12:31:21Z","abstract_excerpt":"The aim of Few-Shot learning methods is to train models which can easily adapt to previously unseen tasks, based on small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic Meta-Learning (MAML). The main idea behind this method is to learn the general weights of the meta-model, which are further adapted to specific problems in a small number of gradient steps. However, the model's main limitation lies in the fact that the update procedure is realized by gradient-based optimisation. In consequence, MAML cannot always modify weights to the essenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15745","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/2205.15745/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":"2205.15745","created_at":"2026-07-05T08:40:51.037023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15745v3","created_at":"2026-07-05T08:40:51.037023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15745","created_at":"2026-07-05T08:40:51.037023+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWP63CKBSVLI","created_at":"2026-07-05T08:40:51.037023+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWP63CKBSVLIWL2N","created_at":"2026-07-05T08:40:51.037023+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWP63CKB","created_at":"2026-07-05T08:40:51.037023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04095","citing_title":"HyperFLINT: Hypernetwork-based Flow Estimation and Temporal Interpolation for Scientific Ensemble Visualization","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4","json":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4.json","graph_json":"https://pith.science/api/pith-number/DWP63CKBSVLIWL2NGT3CPFRRB4/graph.json","events_json":"https://pith.science/api/pith-number/DWP63CKBSVLIWL2NGT3CPFRRB4/events.json","paper":"https://pith.science/paper/DWP63CKB"},"agent_actions":{"view_html":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4","download_json":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4.json","view_paper":"https://pith.science/paper/DWP63CKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15745&json=true","fetch_graph":"https://pith.science/api/pith-number/DWP63CKBSVLIWL2NGT3CPFRRB4/graph.json","fetch_events":"https://pith.science/api/pith-number/DWP63CKBSVLIWL2NGT3CPFRRB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4/action/storage_attestation","attest_author":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4/action/author_attestation","sign_citation":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4/action/citation_signature","submit_replication":"https://pith.science/pith/DWP63CKBSVLIWL2NGT3CPFRRB4/action/replication_record"}},"created_at":"2026-07-05T08:40:51.037023+00:00","updated_at":"2026-07-05T08:40:51.037023+00:00"}