{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ARI72DISEEFBJSDLGVIYNTFRO3","short_pith_number":"pith:ARI72DIS","canonical_record":{"source":{"id":"2012.15723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T17:21:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bec6d4a59628c1657fd8400e7274ced39284cc92085e4ef1fcda3dd597253f56","abstract_canon_sha256":"ea0c0e76c41a38909394828d1febacbbcce18ba173b8afedbb2c4b38f5f2065b"},"schema_version":"1.0"},"canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","source":{"kind":"arxiv","id":"2012.15723","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15723","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15723v2","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15723","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_12","alias_value":"ARI72DISEEFB","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_16","alias_value":"ARI72DISEEFBJSDL","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_8","alias_value":"ARI72DIS","created_at":"2026-07-05T02:45:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ARI72DISEEFBJSDLGVIYNTFRO3","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T17:21:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bec6d4a59628c1657fd8400e7274ced39284cc92085e4ef1fcda3dd597253f56","abstract_canon_sha256":"ea0c0e76c41a38909394828d1febacbbcce18ba173b8afedbb2c4b38f5f2065b"},"schema_version":"1.0"},"canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:35.589817Z","signature_b64":"j3pIWh0CjMq0oecm7rHbHZxTsu0Y7GH6f80ScQ9U4TrLyiizPZ+X1ggT7Ob0etceaBRymHjR7L8fa9H5qHzRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","last_reissued_at":"2026-07-05T02:45:35.589377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:35.589377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15723","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":"2026-07-05T02:45:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwH/YgmM9JMaGiiJmyM5p+5qMHw4WUy0jOnI9FLdfXm+WUR13SlMFgHR2VkGSjpaB33hYTXzmRySVKGS62DiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:06:22.286769Z"},"content_sha256":"9abc34f48b0230f5164f5ed590e4155514bb74ec613cf6d94b19583d998b7438","schema_version":"1.0","event_id":"sha256:9abc34f48b0230f5164f5ed590e4155514bb74ec613cf6d94b19583d998b7438"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ARI72DISEEFBJSDLGVIYNTFRO3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making Pre-trained Language Models Better Few-shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Danqi Chen, Tianyu Gao","submitted_at":"2020-12-31T17:21:26Z","abstract_excerpt":"The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15723","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/2012.15723/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":"2026-07-05T02:45:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BGFhLx7hq2oq5SSxZI0FIWEtrnwSAin9WlBiA4fVI3jmIWT+K+K4LzFdhXmQoGasStbbjdj5HqR+H+BvsGgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:06:22.287931Z"},"content_sha256":"55a4f0733f8738151a0cfda041bc5b7bdc8c364068ad03a445edad834240d9e9","schema_version":"1.0","event_id":"sha256:55a4f0733f8738151a0cfda041bc5b7bdc8c364068ad03a445edad834240d9e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/bundle.json","state_url":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARI72DISEEFBJSDLGVIYNTFRO3/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":"2026-08-07T19:06:22Z","links":{"resolver":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3","bundle":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/bundle.json","state":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARI72DISEEFBJSDLGVIYNTFRO3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ARI72DISEEFBJSDLGVIYNTFRO3","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":"ea0c0e76c41a38909394828d1febacbbcce18ba173b8afedbb2c4b38f5f2065b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T17:21:26Z","title_canon_sha256":"bec6d4a59628c1657fd8400e7274ced39284cc92085e4ef1fcda3dd597253f56"},"schema_version":"1.0","source":{"id":"2012.15723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15723","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15723v2","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15723","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_12","alias_value":"ARI72DISEEFB","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_16","alias_value":"ARI72DISEEFBJSDL","created_at":"2026-07-05T02:45:35Z"},{"alias_kind":"pith_short_8","alias_value":"ARI72DIS","created_at":"2026-07-05T02:45:35Z"}],"graph_snapshots":[{"event_id":"sha256:55a4f0733f8738151a0cfda041bc5b7bdc8c364068ad03a445edad834240d9e9","target":"graph","created_at":"2026-07-05T02:45:35Z","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/2012.15723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together","authors_text":"Adam Fisch, Danqi Chen, Tianyu Gao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T17:21:26Z","title":"Making Pre-trained Language Models Better Few-shot Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15723","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":"sha256:9abc34f48b0230f5164f5ed590e4155514bb74ec613cf6d94b19583d998b7438","target":"record","created_at":"2026-07-05T02:45:35Z","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":"ea0c0e76c41a38909394828d1febacbbcce18ba173b8afedbb2c4b38f5f2065b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T17:21:26Z","title_canon_sha256":"bec6d4a59628c1657fd8400e7274ced39284cc92085e4ef1fcda3dd597253f56"},"schema_version":"1.0","source":{"id":"2012.15723","kind":"arxiv","version":2}},"canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","first_computed_at":"2026-07-05T02:45:35.589377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:35.589377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j3pIWh0CjMq0oecm7rHbHZxTsu0Y7GH6f80ScQ9U4TrLyiizPZ+X1ggT7Ob0etceaBRymHjR7L8fa9H5qHzRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:35.589817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9abc34f48b0230f5164f5ed590e4155514bb74ec613cf6d94b19583d998b7438","sha256:55a4f0733f8738151a0cfda041bc5b7bdc8c364068ad03a445edad834240d9e9"],"state_sha256":"28956eb17d42493c55a49e0982db239482458fc97553f66af9d47773a69f0602"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lwf9Z6yUik1wXmSu9rsDg0bYTL22ksk9HwcUCyGviH/ZtX4wLfnSSr5CVXu9zuXvwWHCy9XHNl3b3RUhfktwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:06:22.311980Z","bundle_sha256":"a4d6c1d14b3444da05f8a56021709b996c9d67904501eedbfe812d736a62b59e"}}