{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HEXL3D3L6GDVAFM2GCHJKF4ZSY","short_pith_number":"pith:HEXL3D3L","schema_version":"1.0","canonical_sha256":"392ebd8f6bf18750159a308e9517999615a6e6ee420c3c4fff213b757c1113bf","source":{"kind":"arxiv","id":"2211.08458","version":3},"attestation_state":"computed","paper":{"title":"Latent Bottlenecked Attentive Neural Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hossein Hajimirsadeghi, Leo Feng, Mohamed Osama Ahmed, Yoshua Bengio","submitted_at":"2022-11-15T19:21:41Z","abstract_excerpt":"Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing sub-quadratic NP variants perform significantly worse than that of TNPs. Tackling this issue, we propose Latent Bottlenecked Attentive Neural Processes (LBANPs), a new computationally efficient sub-q"},"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":"2211.08458","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-15T19:21:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02703b1292066c8bc0ae25073601b596ded105074fbf4a47b1430fc21b417abe","abstract_canon_sha256":"89b365d8422637af4616f902ad57d2077c71280c3c000bfab99d68414635046a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:19.725377Z","signature_b64":"uQoAm8FIXKldFosgypQu2VbEAkSL+ObIaR06JsjdcvvXjLeYv1YGn+bbNrib8aazw54ERF9svxVpsO+wmT4zDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"392ebd8f6bf18750159a308e9517999615a6e6ee420c3c4fff213b757c1113bf","last_reissued_at":"2026-07-05T05:47:19.724877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:19.724877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Bottlenecked Attentive Neural Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hossein Hajimirsadeghi, Leo Feng, Mohamed Osama Ahmed, Yoshua Bengio","submitted_at":"2022-11-15T19:21:41Z","abstract_excerpt":"Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing sub-quadratic NP variants perform significantly worse than that of TNPs. Tackling this issue, we propose Latent Bottlenecked Attentive Neural Processes (LBANPs), a new computationally efficient sub-q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08458","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/2211.08458/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":"2211.08458","created_at":"2026-07-05T05:47:19.724937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08458v3","created_at":"2026-07-05T05:47:19.724937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08458","created_at":"2026-07-05T05:47:19.724937+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEXL3D3L6GDV","created_at":"2026-07-05T05:47:19.724937+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEXL3D3L6GDVAFM2","created_at":"2026-07-05T05:47:19.724937+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEXL3D3L","created_at":"2026-07-05T05:47:19.724937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01172","citing_title":"Revisiting Neural Processes via Fourier Transform and Volterra Series","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY","json":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY.json","graph_json":"https://pith.science/api/pith-number/HEXL3D3L6GDVAFM2GCHJKF4ZSY/graph.json","events_json":"https://pith.science/api/pith-number/HEXL3D3L6GDVAFM2GCHJKF4ZSY/events.json","paper":"https://pith.science/paper/HEXL3D3L"},"agent_actions":{"view_html":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY","download_json":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY.json","view_paper":"https://pith.science/paper/HEXL3D3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08458&json=true","fetch_graph":"https://pith.science/api/pith-number/HEXL3D3L6GDVAFM2GCHJKF4ZSY/graph.json","fetch_events":"https://pith.science/api/pith-number/HEXL3D3L6GDVAFM2GCHJKF4ZSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY/action/storage_attestation","attest_author":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY/action/author_attestation","sign_citation":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY/action/citation_signature","submit_replication":"https://pith.science/pith/HEXL3D3L6GDVAFM2GCHJKF4ZSY/action/replication_record"}},"created_at":"2026-07-05T05:47:19.724937+00:00","updated_at":"2026-07-05T05:47:19.724937+00:00"}