{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R5ZM3VMT3PYO7KE72PQH54V23I","short_pith_number":"pith:R5ZM3VMT","canonical_record":{"source":{"id":"1907.07543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T14:23:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c83b10bb8926528e629c8f4f2546f61c5bc21272bde8914ed04befe7a09e9ee9","abstract_canon_sha256":"b276fd16e0e72b8e9cb0fb8050b5525f6a269524835d117b197e45e23f79d4bb"},"schema_version":"1.0"},"canonical_sha256":"8f72cdd593dbf0efa89fd3e07ef2bada39d794bb2de165dca6454928db90d9f9","source":{"kind":"arxiv","id":"1907.07543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07543","created_at":"2026-05-17T23:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07543v1","created_at":"2026-05-17T23:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07543","created_at":"2026-05-17T23:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"R5ZM3VMT3PYO","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R5ZM3VMT3PYO7KE7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R5ZM3VMT","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R5ZM3VMT3PYO7KE72PQH54V23I","target":"record","payload":{"canonical_record":{"source":{"id":"1907.07543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T14:23:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c83b10bb8926528e629c8f4f2546f61c5bc21272bde8914ed04befe7a09e9ee9","abstract_canon_sha256":"b276fd16e0e72b8e9cb0fb8050b5525f6a269524835d117b197e45e23f79d4bb"},"schema_version":"1.0"},"canonical_sha256":"8f72cdd593dbf0efa89fd3e07ef2bada39d794bb2de165dca6454928db90d9f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:21.821284Z","signature_b64":"fH5qF/dd7YU1Fgbx0JLHy0xOEEcw5kYN0ZJcwGHWg2NsjNwZljRtdt9WtJpJa6EOnCK7G37bxXhxyU/b/vj+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f72cdd593dbf0efa89fd3e07ef2bada39d794bb2de165dca6454928db90d9f9","last_reissued_at":"2026-05-17T23:40:21.820660Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:21.820660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.07543","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":"2026-05-17T23:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoiOkZi6IuCYpdD7Ls7MZTJTntSHv/ts4WWJoWlJzt9zZKA1FnMRtVAHhFGQQi4co/jqcgfriBeEdCPKzg6qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:41:51.932187Z"},"content_sha256":"57619ed183a166a8b800038d8c1efd5a7a3d57a217b551fb1230dc37a1accf34","schema_version":"1.0","event_id":"sha256:57619ed183a166a8b800038d8c1efd5a7a3d57a217b551fb1230dc37a1accf34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R5ZM3VMT3PYO7KE72PQH54V23I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-Shot Classification: A Comparison of Classical and Deep Transfer Machine Learning Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Peter Usherwood, Steven Smit","submitted_at":"2019-07-17T14:23:15Z","abstract_excerpt":"Despite the recent success of deep transfer learning approaches in NLP, there is a lack of quantitative studies demonstrating the gains these models offer in low-shot text classification tasks over existing paradigms. Deep transfer learning approaches such as BERT and ULMFiT demonstrate that they can beat state-of-the-art results on larger datasets, however when one has only 100-1000 labelled examples per class, the choice of approach is less clear, with classical machine learning and deep transfer learning representing valid options. This paper compares the current best transfer learning appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07543","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":""},"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":"2026-05-17T23:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KYe80JgR7naWcPylJkH4J9VPmNR7wvVK1XtAAgnGga8FcpJf0If5bSnfBn+kx9j3rPNqKIYm9DudFhhJ9hmACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:41:51.932891Z"},"content_sha256":"6e200ad697034068f82d6f769a74dbcadd60c0f58bcaf54c34ab87ef78451e71","schema_version":"1.0","event_id":"sha256:6e200ad697034068f82d6f769a74dbcadd60c0f58bcaf54c34ab87ef78451e71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5ZM3VMT3PYO7KE72PQH54V23I/bundle.json","state_url":"https://pith.science/pith/R5ZM3VMT3PYO7KE72PQH54V23I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5ZM3VMT3PYO7KE72PQH54V23I/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":"2026-05-31T06:41:51Z","links":{"resolver":"https://pith.science/pith/R5ZM3VMT3PYO7KE72PQH54V23I","bundle":"https://pith.science/pith/R5ZM3VMT3PYO7KE72PQH54V23I/bundle.json","state":"https://pith.science/pith/R5ZM3VMT3PYO7KE72PQH54V23I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5ZM3VMT3PYO7KE72PQH54V23I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R5ZM3VMT3PYO7KE72PQH54V23I","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":"b276fd16e0e72b8e9cb0fb8050b5525f6a269524835d117b197e45e23f79d4bb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T14:23:15Z","title_canon_sha256":"c83b10bb8926528e629c8f4f2546f61c5bc21272bde8914ed04befe7a09e9ee9"},"schema_version":"1.0","source":{"id":"1907.07543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.07543","created_at":"2026-05-17T23:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"1907.07543v1","created_at":"2026-05-17T23:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07543","created_at":"2026-05-17T23:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"R5ZM3VMT3PYO","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R5ZM3VMT3PYO7KE7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R5ZM3VMT","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:6e200ad697034068f82d6f769a74dbcadd60c0f58bcaf54c34ab87ef78451e71","target":"graph","created_at":"2026-05-17T23:40:21Z","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"},"paper":{"abstract_excerpt":"Despite the recent success of deep transfer learning approaches in NLP, there is a lack of quantitative studies demonstrating the gains these models offer in low-shot text classification tasks over existing paradigms. Deep transfer learning approaches such as BERT and ULMFiT demonstrate that they can beat state-of-the-art results on larger datasets, however when one has only 100-1000 labelled examples per class, the choice of approach is less clear, with classical machine learning and deep transfer learning representing valid options. This paper compares the current best transfer learning appr","authors_text":"Peter Usherwood, Steven Smit","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T14:23:15Z","title":"Low-Shot Classification: A Comparison of Classical and Deep Transfer Machine Learning Approaches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07543","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":"sha256:57619ed183a166a8b800038d8c1efd5a7a3d57a217b551fb1230dc37a1accf34","target":"record","created_at":"2026-05-17T23:40:21Z","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":"b276fd16e0e72b8e9cb0fb8050b5525f6a269524835d117b197e45e23f79d4bb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T14:23:15Z","title_canon_sha256":"c83b10bb8926528e629c8f4f2546f61c5bc21272bde8914ed04befe7a09e9ee9"},"schema_version":"1.0","source":{"id":"1907.07543","kind":"arxiv","version":1}},"canonical_sha256":"8f72cdd593dbf0efa89fd3e07ef2bada39d794bb2de165dca6454928db90d9f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f72cdd593dbf0efa89fd3e07ef2bada39d794bb2de165dca6454928db90d9f9","first_computed_at":"2026-05-17T23:40:21.820660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:21.820660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fH5qF/dd7YU1Fgbx0JLHy0xOEEcw5kYN0ZJcwGHWg2NsjNwZljRtdt9WtJpJa6EOnCK7G37bxXhxyU/b/vj+DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:21.821284Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.07543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57619ed183a166a8b800038d8c1efd5a7a3d57a217b551fb1230dc37a1accf34","sha256:6e200ad697034068f82d6f769a74dbcadd60c0f58bcaf54c34ab87ef78451e71"],"state_sha256":"c3e7d2e27633fc9ab70bd8cdd8b88424683bfc45f19909dcfbd356fe8c10c7b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RtPl5mToo7eSpH1aJBayy98bdo02lxJUt5/miwAIw5jMmLWad2c/aMhDFHD0JGcNWbk7u278hHwMzmGkCvBRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:41:51.936594Z","bundle_sha256":"3ea93540ec8fe87817a85891340579a4c13cf75cefe8e6b712e86492843b1158"}}