{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TQR5JVJ7OIYGJLBJHOTL4NR7SW","short_pith_number":"pith:TQR5JVJ7","canonical_record":{"source":{"id":"2109.04332","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T15:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"fce787e121f521682ca826a32f7423092c662aec77b37f6cee922938bc9b756d","abstract_canon_sha256":"e448b227d73cdb3a44aabf50ec117924add4cfb8bae7809e4af7c15f371c29b1"},"schema_version":"1.0"},"canonical_sha256":"9c23d4d53f723064ac293ba6be363f95b86aa37b244b0bb8c00887e9dd0cdb09","source":{"kind":"arxiv","id":"2109.04332","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04332","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04332v3","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04332","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"TQR5JVJ7OIYG","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"TQR5JVJ7OIYGJLBJ","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"TQR5JVJ7","created_at":"2026-07-05T04:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TQR5JVJ7OIYGJLBJHOTL4NR7SW","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04332","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T15:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"fce787e121f521682ca826a32f7423092c662aec77b37f6cee922938bc9b756d","abstract_canon_sha256":"e448b227d73cdb3a44aabf50ec117924add4cfb8bae7809e4af7c15f371c29b1"},"schema_version":"1.0"},"canonical_sha256":"9c23d4d53f723064ac293ba6be363f95b86aa37b244b0bb8c00887e9dd0cdb09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:41.267913Z","signature_b64":"D9NqJNrYt8biPbaD7aTfetMqgR8aDvopcgA5r32c54ICX2mvHfqvoXioZsWgWFfD4J7tLl8EJaVDiaAvsXXwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c23d4d53f723064ac293ba6be363f95b86aa37b244b0bb8c00887e9dd0cdb09","last_reissued_at":"2026-07-05T04:04:41.267452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:41.267452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04332","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2WfdkgpA4gjldr3JEFIsAk9yUo9GLDthl9Mdl/DOIkrL7kYkTERcHZjOBsPW7gjttaE4FEY4SBeYCVi3ZnIhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:12:03.744885Z"},"content_sha256":"d2e2ffa5e8fa4ca5228d85e21c4f010c8e52d23dcce855e12d75ec6df8a7d13e","schema_version":"1.0","event_id":"sha256:d2e2ffa5e8fa4ca5228d85e21c4f010c8e52d23dcce855e12d75ec6df8a7d13e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TQR5JVJ7OIYGJLBJHOTL4NR7SW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Minlie Huang, Xu Han, Yuxian Gu, Zhiyuan Liu","submitted_at":"2021-09-09T15:11:04Z","abstract_excerpt":"Prompts for pre-trained language models (PLMs) have shown remarkable performance by bridging the gap between pre-training tasks and various downstream tasks. Among these methods, prompt tuning, which freezes PLMs and only tunes soft prompts, provides an efficient and effective solution for adapting large-scale PLMs to downstream tasks. However, prompt tuning is yet to be fully explored. In our pilot experiments, we find that prompt tuning performs comparably with conventional full-model fine-tuning when downstream data are sufficient, whereas it performs much worse under few-shot learning sett"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04332","kind":"arxiv","version":3},"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/2109.04332/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":"2026-07-05T04:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mk630cQhc186HKhIZUGhLpq+c+lrm3ednscXb0rrJyFF546VM0y9ro/CLSP/X3xYxI9+q49+T8y1nCNTgW9XDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:12:03.745380Z"},"content_sha256":"eeedef9a2be9ffe827ca1d39cffebd788c5ee6f3b4ff3f9ce82af39a2e152de8","schema_version":"1.0","event_id":"sha256:eeedef9a2be9ffe827ca1d39cffebd788c5ee6f3b4ff3f9ce82af39a2e152de8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW/bundle.json","state_url":"https://pith.science/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW/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":"2026-08-09T13:12:03Z","links":{"resolver":"https://pith.science/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW","bundle":"https://pith.science/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW/bundle.json","state":"https://pith.science/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQR5JVJ7OIYGJLBJHOTL4NR7SW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TQR5JVJ7OIYGJLBJHOTL4NR7SW","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":"e448b227d73cdb3a44aabf50ec117924add4cfb8bae7809e4af7c15f371c29b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T15:11:04Z","title_canon_sha256":"fce787e121f521682ca826a32f7423092c662aec77b37f6cee922938bc9b756d"},"schema_version":"1.0","source":{"id":"2109.04332","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04332","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04332v3","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04332","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"TQR5JVJ7OIYG","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"TQR5JVJ7OIYGJLBJ","created_at":"2026-07-05T04:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"TQR5JVJ7","created_at":"2026-07-05T04:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:eeedef9a2be9ffe827ca1d39cffebd788c5ee6f3b4ff3f9ce82af39a2e152de8","target":"graph","created_at":"2026-07-05T04:04:41Z","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/2109.04332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompts for pre-trained language models (PLMs) have shown remarkable performance by bridging the gap between pre-training tasks and various downstream tasks. Among these methods, prompt tuning, which freezes PLMs and only tunes soft prompts, provides an efficient and effective solution for adapting large-scale PLMs to downstream tasks. However, prompt tuning is yet to be fully explored. In our pilot experiments, we find that prompt tuning performs comparably with conventional full-model fine-tuning when downstream data are sufficient, whereas it performs much worse under few-shot learning sett","authors_text":"Minlie Huang, Xu Han, Yuxian Gu, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T15:11:04Z","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04332","kind":"arxiv","version":3},"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:d2e2ffa5e8fa4ca5228d85e21c4f010c8e52d23dcce855e12d75ec6df8a7d13e","target":"record","created_at":"2026-07-05T04:04:41Z","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":"e448b227d73cdb3a44aabf50ec117924add4cfb8bae7809e4af7c15f371c29b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T15:11:04Z","title_canon_sha256":"fce787e121f521682ca826a32f7423092c662aec77b37f6cee922938bc9b756d"},"schema_version":"1.0","source":{"id":"2109.04332","kind":"arxiv","version":3}},"canonical_sha256":"9c23d4d53f723064ac293ba6be363f95b86aa37b244b0bb8c00887e9dd0cdb09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c23d4d53f723064ac293ba6be363f95b86aa37b244b0bb8c00887e9dd0cdb09","first_computed_at":"2026-07-05T04:04:41.267452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:41.267452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D9NqJNrYt8biPbaD7aTfetMqgR8aDvopcgA5r32c54ICX2mvHfqvoXioZsWgWFfD4J7tLl8EJaVDiaAvsXXwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:41.267913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04332","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2e2ffa5e8fa4ca5228d85e21c4f010c8e52d23dcce855e12d75ec6df8a7d13e","sha256:eeedef9a2be9ffe827ca1d39cffebd788c5ee6f3b4ff3f9ce82af39a2e152de8"],"state_sha256":"ebe64b9de2cb2d3ffad69428566f41e1a3bdb09a9b9803d5d827ff3ad94a585c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SWv1phbwXD0r6KBQrBRc3qX7zPdTcnV5vhuINewqFoVLlzsAcuxeSOC3/o3f6XbIa70uF5F4TOjVpn7fJmitBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:12:03.749800Z","bundle_sha256":"d8cecd4ede24a34337bf2a2429f2ee92827c3930cec0226d711cfe77d1fe92aa"}}