{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ODQHCD64L7LMJON7GPCK3XFBPX","short_pith_number":"pith:ODQHCD64","canonical_record":{"source":{"id":"2108.02035","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T13:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"5f46b0a3a0d7bc721190bd7a12da7d65bc8f8528a1fdacb9914c3308bfbb3242","abstract_canon_sha256":"f3df74e85dd5b6d2d31fcb1b736a18a360e311f730c5a45dd8ee784f7b64e16c"},"schema_version":"1.0"},"canonical_sha256":"70e0710fdc5fd6c4b9bf33c4addca17dc5df3b9227c363010c76e4c28ebceca4","source":{"kind":"arxiv","id":"2108.02035","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02035","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02035v2","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02035","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"ODQHCD64L7LM","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"ODQHCD64L7LMJON7","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"ODQHCD64","created_at":"2026-07-05T04:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ODQHCD64L7LMJON7GPCK3XFBPX","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02035","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T13:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"5f46b0a3a0d7bc721190bd7a12da7d65bc8f8528a1fdacb9914c3308bfbb3242","abstract_canon_sha256":"f3df74e85dd5b6d2d31fcb1b736a18a360e311f730c5a45dd8ee784f7b64e16c"},"schema_version":"1.0"},"canonical_sha256":"70e0710fdc5fd6c4b9bf33c4addca17dc5df3b9227c363010c76e4c28ebceca4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:16.214892Z","signature_b64":"WVAiBZLX59mG1EdwxC2a4CwAea/dTnZrQRYLFzORlALkOR5NnnZ+FZ823ooSyhwJbe1LFGuhi8KIK+N4vgZoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70e0710fdc5fd6c4b9bf33c4addca17dc5df3b9227c363010c76e4c28ebceca4","last_reissued_at":"2026-07-05T04:06:16.214358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:16.214358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02035","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":"2026-07-05T04:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cruQRK/pel/cmg9RPIix+DGzlsBUxv3il5wHx754VTmc6LhmT14iPrfW3VG7ar4/sXRkm5YSIvpS4A3QwiqfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T00:42:47.772122Z"},"content_sha256":"b49094123f29a0c039e323f064b38a60ab479af0e3cdd9f26f07541ca5bb0bba","schema_version":"1.0","event_id":"sha256:b49094123f29a0c039e323f064b38a60ab479af0e3cdd9f26f07541ca5bb0bba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ODQHCD64L7LMJON7GPCK3XFBPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huadong Wang, Jingang Wang, Juanzi Li, Maosong Sun, Ning Ding, Shengding Hu, Wei Wu, Zhiyuan Liu","submitted_at":"2021-08-04T13:00:16Z","abstract_excerpt":"Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over the generic fine-tuning methods with extra classifiers. The core idea of prompt-tuning is to insert text pieces, i.e., template, to the input and transform a classification problem into a masked language modeling problem, where a crucial step is to construct a projection, i.e., verbalizer, between a label space and a label word space. A verbalizer is usually "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02035","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/2108.02035/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":"2026-07-05T04:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4jrXagUAFakRrz7Nary/plEzMPro9VvCxYe9rIRFfAg25VSRZci/+ET7lOXj06YwteBsZ6u1D03FLFm0he3NBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T00:42:47.772513Z"},"content_sha256":"7846d7ac3fbaabef88273ea6190b9529cdf95b494874c43181438e0b49271e0f","schema_version":"1.0","event_id":"sha256:7846d7ac3fbaabef88273ea6190b9529cdf95b494874c43181438e0b49271e0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ODQHCD64L7LMJON7GPCK3XFBPX/bundle.json","state_url":"https://pith.science/pith/ODQHCD64L7LMJON7GPCK3XFBPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ODQHCD64L7LMJON7GPCK3XFBPX/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":"2026-07-25T00:42:47Z","links":{"resolver":"https://pith.science/pith/ODQHCD64L7LMJON7GPCK3XFBPX","bundle":"https://pith.science/pith/ODQHCD64L7LMJON7GPCK3XFBPX/bundle.json","state":"https://pith.science/pith/ODQHCD64L7LMJON7GPCK3XFBPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ODQHCD64L7LMJON7GPCK3XFBPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ODQHCD64L7LMJON7GPCK3XFBPX","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":"f3df74e85dd5b6d2d31fcb1b736a18a360e311f730c5a45dd8ee784f7b64e16c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T13:00:16Z","title_canon_sha256":"5f46b0a3a0d7bc721190bd7a12da7d65bc8f8528a1fdacb9914c3308bfbb3242"},"schema_version":"1.0","source":{"id":"2108.02035","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02035","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02035v2","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02035","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"ODQHCD64L7LM","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"ODQHCD64L7LMJON7","created_at":"2026-07-05T04:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"ODQHCD64","created_at":"2026-07-05T04:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:7846d7ac3fbaabef88273ea6190b9529cdf95b494874c43181438e0b49271e0f","target":"graph","created_at":"2026-07-05T04:06:16Z","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/2108.02035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over the generic fine-tuning methods with extra classifiers. The core idea of prompt-tuning is to insert text pieces, i.e., template, to the input and transform a classification problem into a masked language modeling problem, where a crucial step is to construct a projection, i.e., verbalizer, between a label space and a label word space. A verbalizer is usually ","authors_text":"Huadong Wang, Jingang Wang, Juanzi Li, Maosong Sun, Ning Ding, Shengding Hu, Wei Wu, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T13:00:16Z","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02035","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:b49094123f29a0c039e323f064b38a60ab479af0e3cdd9f26f07541ca5bb0bba","target":"record","created_at":"2026-07-05T04:06:16Z","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":"f3df74e85dd5b6d2d31fcb1b736a18a360e311f730c5a45dd8ee784f7b64e16c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T13:00:16Z","title_canon_sha256":"5f46b0a3a0d7bc721190bd7a12da7d65bc8f8528a1fdacb9914c3308bfbb3242"},"schema_version":"1.0","source":{"id":"2108.02035","kind":"arxiv","version":2}},"canonical_sha256":"70e0710fdc5fd6c4b9bf33c4addca17dc5df3b9227c363010c76e4c28ebceca4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70e0710fdc5fd6c4b9bf33c4addca17dc5df3b9227c363010c76e4c28ebceca4","first_computed_at":"2026-07-05T04:06:16.214358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:16.214358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVAiBZLX59mG1EdwxC2a4CwAea/dTnZrQRYLFzORlALkOR5NnnZ+FZ823ooSyhwJbe1LFGuhi8KIK+N4vgZoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:16.214892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02035","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b49094123f29a0c039e323f064b38a60ab479af0e3cdd9f26f07541ca5bb0bba","sha256:7846d7ac3fbaabef88273ea6190b9529cdf95b494874c43181438e0b49271e0f"],"state_sha256":"3db2342c9d3d3ac35d63b1bff02d3cf5402a5d0c940ac4f162e6ecc18a78e1a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z210zNXNGFPtBuy+do3rUansXwqNBD26BEEQC465nGQjGp76HfcKY2sidHS/PiL7Zf4H0D/hUeWxkRIhrdojBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T00:42:47.774995Z","bundle_sha256":"1e2992cccd84f6c4873998320755ff1374e9583e0ed3b1595348519600addab3"}}