{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NKRJTWSWVDW47G5564BAFUU6ST","short_pith_number":"pith:NKRJTWSW","schema_version":"1.0","canonical_sha256":"6aa299da56a8edcf9bbdf70202d29e94e79d3bc900d51f0c7f5a109368409123","source":{"kind":"arxiv","id":"2207.04179","version":2},"attestation_state":"computed","paper":{"title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Grover, Tung Nguyen","submitted_at":"2022-07-09T02:28:58Z","abstract_excerpt":"Neural Processes (NPs) are a popular class of approaches for meta-learning. Similar to Gaussian Processes (GPs), NPs define distributions over functions and can estimate uncertainty in their predictions. However, unlike GPs, NPs and their variants suffer from underfitting and often have intractable likelihoods, which limit their applications in sequential decision making. We propose Transformer Neural Processes (TNPs), a new member of the NP family that casts uncertainty-aware meta learning as a sequence modeling problem. We learn TNPs via an autoregressive likelihood-based objective and insta"},"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":"2207.04179","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T02:28:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bdb764378b9ff49ae4d607da27fefad26c383408e8265d1e88d93b409e1b7e9","abstract_canon_sha256":"3aeb355381a7c439249dd4bfcf81a309e56b32c71a12aad38a70d386195eeb5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:52.118782Z","signature_b64":"DkGPtOqlQ2RzK/axYXAZCCgcD/TJh7myo1ALhliPlq+io0uHXQM68huz1HwhcS+aFj4DGzXnwxHWntXjETdfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa299da56a8edcf9bbdf70202d29e94e79d3bc900d51f0c7f5a109368409123","last_reissued_at":"2026-07-05T05:39:52.118362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:52.118362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Grover, Tung Nguyen","submitted_at":"2022-07-09T02:28:58Z","abstract_excerpt":"Neural Processes (NPs) are a popular class of approaches for meta-learning. Similar to Gaussian Processes (GPs), NPs define distributions over functions and can estimate uncertainty in their predictions. However, unlike GPs, NPs and their variants suffer from underfitting and often have intractable likelihoods, which limit their applications in sequential decision making. We propose Transformer Neural Processes (TNPs), a new member of the NP family that casts uncertainty-aware meta learning as a sequence modeling problem. We learn TNPs via an autoregressive likelihood-based objective and insta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04179","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/2207.04179/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":"2207.04179","created_at":"2026-07-05T05:39:52.118420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04179v2","created_at":"2026-07-05T05:39:52.118420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04179","created_at":"2026-07-05T05:39:52.118420+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKRJTWSWVDW4","created_at":"2026-07-05T05:39:52.118420+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKRJTWSWVDW47G55","created_at":"2026-07-05T05:39:52.118420+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKRJTWSW","created_at":"2026-07-05T05:39:52.118420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08786","citing_title":"PRIM: Meta-Learned Bayesian Root Cause Analysis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01172","citing_title":"Revisiting Neural Processes via Fourier Transform and Volterra Series","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2411.12502","citing_title":"Transformer Neural Processes - Kernel Regression","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08786","citing_title":"PRIM: Meta-Learned Bayesian Root Cause Analysis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09163","citing_title":"Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08786","citing_title":"PRIM: Meta-Learned Bayesian Root Cause Analysis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09498","citing_title":"Spectral Transformer Neural Processes","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST","json":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST.json","graph_json":"https://pith.science/api/pith-number/NKRJTWSWVDW47G5564BAFUU6ST/graph.json","events_json":"https://pith.science/api/pith-number/NKRJTWSWVDW47G5564BAFUU6ST/events.json","paper":"https://pith.science/paper/NKRJTWSW"},"agent_actions":{"view_html":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST","download_json":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST.json","view_paper":"https://pith.science/paper/NKRJTWSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04179&json=true","fetch_graph":"https://pith.science/api/pith-number/NKRJTWSWVDW47G5564BAFUU6ST/graph.json","fetch_events":"https://pith.science/api/pith-number/NKRJTWSWVDW47G5564BAFUU6ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST/action/storage_attestation","attest_author":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST/action/author_attestation","sign_citation":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST/action/citation_signature","submit_replication":"https://pith.science/pith/NKRJTWSWVDW47G5564BAFUU6ST/action/replication_record"}},"created_at":"2026-07-05T05:39:52.118420+00:00","updated_at":"2026-07-05T05:39:52.118420+00:00"}