{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A43Y3IZXB2AWA55T3V4Z5ZCPVH","short_pith_number":"pith:A43Y3IZX","canonical_record":{"source":{"id":"2210.13979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T05:22:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4b468b5b00e059f34e71853e7ebcfa288935378da6414d99850f5b6acebf704b","abstract_canon_sha256":"d5023b3a81b5cd977b3e3ee73882087a68245215cf01abc64ff2005d07645dd7"},"schema_version":"1.0"},"canonical_sha256":"07378da3370e816077b3dd799ee44fa9ceda0052da1da8d581a30cf9d652aef6","source":{"kind":"arxiv","id":"2210.13979","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13979","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13979v2","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13979","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"A43Y3IZXB2AW","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"A43Y3IZXB2AWA55T","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"A43Y3IZX","created_at":"2026-07-05T05:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A43Y3IZXB2AWA55T3V4Z5ZCPVH","target":"record","payload":{"canonical_record":{"source":{"id":"2210.13979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T05:22:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4b468b5b00e059f34e71853e7ebcfa288935378da6414d99850f5b6acebf704b","abstract_canon_sha256":"d5023b3a81b5cd977b3e3ee73882087a68245215cf01abc64ff2005d07645dd7"},"schema_version":"1.0"},"canonical_sha256":"07378da3370e816077b3dd799ee44fa9ceda0052da1da8d581a30cf9d652aef6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:00.488280Z","signature_b64":"0JiWBzxAbSTvYo5r/a1i+WJJtRDqOHnCtJEd4Orm1dkaYLDIQdHaDZB4+5s+jo+ygaD37Bfbu8KX1OuDFcRmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07378da3370e816077b3dd799ee44fa9ceda0052da1da8d581a30cf9d652aef6","last_reissued_at":"2026-07-05T05:15:00.487826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:00.487826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.13979","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IA15JYVA7dq9mdzitiyppSAiitDz53j6PeEa7LufSa1Wtt7PK/fmjhfKyDL9OeKhtK/htAmXaoQhvm16Ecf6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:48:51.129432Z"},"content_sha256":"8acc0bd5c6b293c562b9385f39597eeaec36583279ab14f12f68718e1ec78818","schema_version":"1.0","event_id":"sha256:8acc0bd5c6b293c562b9385f39597eeaec36583279ab14f12f68718e1ec78818"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A43Y3IZXB2AWA55T3V4Z5ZCPVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anasuya Das, Arijit Sehanobish, Benjamin Odry, Kawshik Kannan, Nabila Abraham","submitted_at":"2022-10-22T05:22:29Z","abstract_excerpt":"Large pretrained Transformer-based language models like BERT and GPT have changed the landscape of Natural Language Processing (NLP). However, fine tuning such models still requires a large number of training examples for each target task, thus annotating multiple datasets and training these models on various downstream tasks becomes time consuming and expensive. In this work, we propose a simple extension of the Prototypical Networks for few-shot text classification. Our main idea is to replace the class prototypes by Gaussians and introduce a regularization term that encourages the examples "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13979","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/2210.13979/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZbXMIzj9Osb/rRdEIXDCT7TXF2SFS0O5FiQAt+E2kyNaMJob6Nk9fWKoP8ttc+ZYZReL6c3FskrN+iObndACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:48:51.130370Z"},"content_sha256":"edfa0f5914fe3f98b68c40a5b7b98baa9aa822cad0b27bb91cc4a56753156b85","schema_version":"1.0","event_id":"sha256:edfa0f5914fe3f98b68c40a5b7b98baa9aa822cad0b27bb91cc4a56753156b85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH/bundle.json","state_url":"https://pith.science/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T01:48:51Z","links":{"resolver":"https://pith.science/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH","bundle":"https://pith.science/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH/bundle.json","state":"https://pith.science/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A43Y3IZXB2AWA55T3V4Z5ZCPVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A43Y3IZXB2AWA55T3V4Z5ZCPVH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d5023b3a81b5cd977b3e3ee73882087a68245215cf01abc64ff2005d07645dd7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T05:22:29Z","title_canon_sha256":"4b468b5b00e059f34e71853e7ebcfa288935378da6414d99850f5b6acebf704b"},"schema_version":"1.0","source":{"id":"2210.13979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13979","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13979v2","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13979","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"A43Y3IZXB2AW","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"A43Y3IZXB2AWA55T","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"A43Y3IZX","created_at":"2026-07-05T05:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:edfa0f5914fe3f98b68c40a5b7b98baa9aa822cad0b27bb91cc4a56753156b85","target":"graph","created_at":"2026-07-05T05:15:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.13979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained Transformer-based language models like BERT and GPT have changed the landscape of Natural Language Processing (NLP). However, fine tuning such models still requires a large number of training examples for each target task, thus annotating multiple datasets and training these models on various downstream tasks becomes time consuming and expensive. In this work, we propose a simple extension of the Prototypical Networks for few-shot text classification. Our main idea is to replace the class prototypes by Gaussians and introduce a regularization term that encourages the examples ","authors_text":"Anasuya Das, Arijit Sehanobish, Benjamin Odry, Kawshik Kannan, Nabila Abraham","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T05:22:29Z","title":"Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13979","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8acc0bd5c6b293c562b9385f39597eeaec36583279ab14f12f68718e1ec78818","target":"record","created_at":"2026-07-05T05:15:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d5023b3a81b5cd977b3e3ee73882087a68245215cf01abc64ff2005d07645dd7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T05:22:29Z","title_canon_sha256":"4b468b5b00e059f34e71853e7ebcfa288935378da6414d99850f5b6acebf704b"},"schema_version":"1.0","source":{"id":"2210.13979","kind":"arxiv","version":2}},"canonical_sha256":"07378da3370e816077b3dd799ee44fa9ceda0052da1da8d581a30cf9d652aef6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07378da3370e816077b3dd799ee44fa9ceda0052da1da8d581a30cf9d652aef6","first_computed_at":"2026-07-05T05:15:00.487826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:00.487826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JiWBzxAbSTvYo5r/a1i+WJJtRDqOHnCtJEd4Orm1dkaYLDIQdHaDZB4+5s+jo+ygaD37Bfbu8KX1OuDFcRmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:00.488280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8acc0bd5c6b293c562b9385f39597eeaec36583279ab14f12f68718e1ec78818","sha256:edfa0f5914fe3f98b68c40a5b7b98baa9aa822cad0b27bb91cc4a56753156b85"],"state_sha256":"0b87813f060dccb8264611bede679e9c4582fd73c2e9b9cb0d574617cf57d7c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dApcrFj+fc68S8Bf4foP2sqPMiihFfYiVwxpEQEkAB9ubuJ2pnQNxtEeBJCuJcw6WoarwFEnSUKVEpdw+5oXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:48:51.137968Z","bundle_sha256":"5a5d155026db70c5c3b1399881dd9e7af5787c34506bee59eaaab0d29af195ae"}}