{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LXNMJY7ELNHG5KIIGHMDHEJOR6","short_pith_number":"pith:LXNMJY7E","canonical_record":{"source":{"id":"2211.13638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T14:38:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66e9530db23aaaf84bb7d83951f85d374199a5b80d92e2cc002d5e34d6ecf31e","abstract_canon_sha256":"5dc2c21769c5f2b84eccd6f9e045e7aabb271e71882ad69cc3fff19c206b1743"},"schema_version":"1.0"},"canonical_sha256":"5ddac4e3e45b4e6ea90831d833912e8f87defcaaf2513d029c134e85194d0230","source":{"kind":"arxiv","id":"2211.13638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13638","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13638v1","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13638","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"LXNMJY7ELNHG","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"LXNMJY7ELNHG5KII","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"LXNMJY7E","created_at":"2026-07-05T05:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LXNMJY7ELNHG5KIIGHMDHEJOR6","target":"record","payload":{"canonical_record":{"source":{"id":"2211.13638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T14:38:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66e9530db23aaaf84bb7d83951f85d374199a5b80d92e2cc002d5e34d6ecf31e","abstract_canon_sha256":"5dc2c21769c5f2b84eccd6f9e045e7aabb271e71882ad69cc3fff19c206b1743"},"schema_version":"1.0"},"canonical_sha256":"5ddac4e3e45b4e6ea90831d833912e8f87defcaaf2513d029c134e85194d0230","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:24.765312Z","signature_b64":"7I+AyqFP3zhnKxK/UHc24dllUphLrbxkmNKWSEO+BBPnyOWBK2DocebRddxVHOCKuVpzCxPRpKOKcypGxDwgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ddac4e3e45b4e6ea90831d833912e8f87defcaaf2513d029c134e85194d0230","last_reissued_at":"2026-07-05T05:19:24.764775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:24.764775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.13638","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"44cVs3yYRcY6ly/2S4wpqHeyEXpNwsvUEeIxUr9GLCbQ4Z6waZf0F3S7sGzL/Ui3yEgX+gZJe9pLbv0jLEOlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:49:08.578989Z"},"content_sha256":"5007f4239b2ebe673b3183d178ff754a599a2eb71edbfd584560cfd234f5e19b","schema_version":"1.0","event_id":"sha256:5007f4239b2ebe673b3183d178ff754a599a2eb71edbfd584560cfd234f5e19b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LXNMJY7ELNHG5KIIGHMDHEJOR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Xing Xie, Xiting Wang, Yaru Hao, Yiqiao Jin, Yizhou Sun","submitted_at":"2022-11-24T14:38:08Z","abstract_excerpt":"In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which automatically learns a bias to improve predictive performance for varying data sizes, especially low-resource settings. Our prototypical fine-tuning approach can automatically adjust the model capacity according to the number of data points and the model's inherent attributes. Moreover, we propose four principles for effective prototype fine-tuning towards the optima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13638","kind":"arxiv","version":1},"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/2211.13638/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":"2026-07-05T05:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCD1Nftevm3TbWLufqHxrsuKWgkp5Q5y8KzWWVM4xWkNnuUtcMemuCW0Q34bgrzKHMgU7ihau+RqpYAkxQvaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:49:08.579981Z"},"content_sha256":"2ae2189aa90c991f61ab34f91abb3cef6452f654ee49e99be87278a4e077f736","schema_version":"1.0","event_id":"sha256:2ae2189aa90c991f61ab34f91abb3cef6452f654ee49e99be87278a4e077f736"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6/bundle.json","state_url":"https://pith.science/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6/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":"2026-08-05T00:49:08Z","links":{"resolver":"https://pith.science/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6","bundle":"https://pith.science/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6/bundle.json","state":"https://pith.science/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LXNMJY7ELNHG5KIIGHMDHEJOR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LXNMJY7ELNHG5KIIGHMDHEJOR6","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":"5dc2c21769c5f2b84eccd6f9e045e7aabb271e71882ad69cc3fff19c206b1743","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T14:38:08Z","title_canon_sha256":"66e9530db23aaaf84bb7d83951f85d374199a5b80d92e2cc002d5e34d6ecf31e"},"schema_version":"1.0","source":{"id":"2211.13638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13638","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13638v1","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13638","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"LXNMJY7ELNHG","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"LXNMJY7ELNHG5KII","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"LXNMJY7E","created_at":"2026-07-05T05:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:2ae2189aa90c991f61ab34f91abb3cef6452f654ee49e99be87278a4e077f736","target":"graph","created_at":"2026-07-05T05:19:24Z","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/2211.13638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which automatically learns a bias to improve predictive performance for varying data sizes, especially low-resource settings. Our prototypical fine-tuning approach can automatically adjust the model capacity according to the number of data points and the model's inherent attributes. Moreover, we propose four principles for effective prototype fine-tuning towards the optima","authors_text":"Xing Xie, Xiting Wang, Yaru Hao, Yiqiao Jin, Yizhou Sun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T14:38:08Z","title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13638","kind":"arxiv","version":1},"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":"sha256:5007f4239b2ebe673b3183d178ff754a599a2eb71edbfd584560cfd234f5e19b","target":"record","created_at":"2026-07-05T05:19:24Z","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":"5dc2c21769c5f2b84eccd6f9e045e7aabb271e71882ad69cc3fff19c206b1743","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T14:38:08Z","title_canon_sha256":"66e9530db23aaaf84bb7d83951f85d374199a5b80d92e2cc002d5e34d6ecf31e"},"schema_version":"1.0","source":{"id":"2211.13638","kind":"arxiv","version":1}},"canonical_sha256":"5ddac4e3e45b4e6ea90831d833912e8f87defcaaf2513d029c134e85194d0230","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ddac4e3e45b4e6ea90831d833912e8f87defcaaf2513d029c134e85194d0230","first_computed_at":"2026-07-05T05:19:24.764775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:24.764775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7I+AyqFP3zhnKxK/UHc24dllUphLrbxkmNKWSEO+BBPnyOWBK2DocebRddxVHOCKuVpzCxPRpKOKcypGxDwgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:24.765312Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5007f4239b2ebe673b3183d178ff754a599a2eb71edbfd584560cfd234f5e19b","sha256:2ae2189aa90c991f61ab34f91abb3cef6452f654ee49e99be87278a4e077f736"],"state_sha256":"04cb9ee72134576d38da89621138304b2466901ae6b858f326d33087b337d1d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJ2jmewjy06yG7XMHoPHQzBjOHEKnEQoGnUnPEK8m9HYZrww1jNsv9IPNoB0G3YwqCNJ/un1r1FH+0t5K5auAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:49:08.588140Z","bundle_sha256":"77c744951ae0d0ca3c94ef8dfc251db9538a5fd462d7ba2ca2f2989918001bb1"}}