{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FBPMLRP46RVAEV7CXLHBYUVSI6","short_pith_number":"pith:FBPMLRP4","canonical_record":{"source":{"id":"2201.05411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T12:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"e7777bb6e928643b82905e12eb2f1917fc70a28f2c220c807e28702ea4f9b46a","abstract_canon_sha256":"612369a6bc8e31e4d6a8ac1743e970260284be9bb5d80af7b465be83c7e0bb6a"},"schema_version":"1.0"},"canonical_sha256":"285ec5c5fcf46a0257e2bace1c52b24784d61a592ad65004cfa9826c9e3687ea","source":{"kind":"arxiv","id":"2201.05411","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05411","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05411v1","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05411","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"FBPMLRP46RVA","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"FBPMLRP46RVAEV7C","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"FBPMLRP4","created_at":"2026-07-05T03:48:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FBPMLRP46RVAEV7CXLHBYUVSI6","target":"record","payload":{"canonical_record":{"source":{"id":"2201.05411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T12:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"e7777bb6e928643b82905e12eb2f1917fc70a28f2c220c807e28702ea4f9b46a","abstract_canon_sha256":"612369a6bc8e31e4d6a8ac1743e970260284be9bb5d80af7b465be83c7e0bb6a"},"schema_version":"1.0"},"canonical_sha256":"285ec5c5fcf46a0257e2bace1c52b24784d61a592ad65004cfa9826c9e3687ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:32.178386Z","signature_b64":"hGNN0SV0P1/HWY+Dr62q37yklC0TZUmXYFM6fP2Mqfo5aGjREXkwimFrGHNvb4tQs6akHpAJOdf9aKttJXO0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"285ec5c5fcf46a0257e2bace1c52b24784d61a592ad65004cfa9826c9e3687ea","last_reissued_at":"2026-07-05T03:48:32.177915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:32.177915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.05411","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":"2026-07-05T03:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRuIy0xVbjlg7byrEL1mwmgtpZd5hB1D4krCbGBkY+Dqxb+hoFQIypyGKeuxe9t0KLr904KIDUSfw52IcY5OCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:00:19.714250Z"},"content_sha256":"1bc877e4315a064c10adca82f61b08374afc588ecdfa96ad97ddc7687c4c3a53","schema_version":"1.0","event_id":"sha256:1bc877e4315a064c10adca82f61b08374afc588ecdfa96ad97ddc7687c4c3a53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FBPMLRP46RVAEV7CXLHBYUVSI6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Tong Mo, Weiping Li, Wen Zhao, Yinyi Wei, Yongtao Jiang","submitted_at":"2022-01-14T12:04:37Z","abstract_excerpt":"Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label word space, prompt-tuning can achieve excellent results in zero-shot and few-shot scenarios. However, typical prompt-tuning needs a manually designed verbalizer which requires domain expertise and human efforts. And the insufficient label space may introduce considerable bias into the results. In this paper, we focus on eliciting knowledge from pretrained language models and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05411","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/2201.05411/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":"2026-07-05T03:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"siJh3rMadhfz7/zYPAAUoMYM3t4krxBFp+qxUsostthnwBok+Z5GMvEhAsBZKpOfc3Y+4YuyCB232JNIFmS8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:00:19.714570Z"},"content_sha256":"9ad6ea9c89c8650664a0c3569b35098957105b5dfb8ac9df318df3fba0e70d92","schema_version":"1.0","event_id":"sha256:9ad6ea9c89c8650664a0c3569b35098957105b5dfb8ac9df318df3fba0e70d92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBPMLRP46RVAEV7CXLHBYUVSI6/bundle.json","state_url":"https://pith.science/pith/FBPMLRP46RVAEV7CXLHBYUVSI6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBPMLRP46RVAEV7CXLHBYUVSI6/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":"2026-08-06T20:00:19Z","links":{"resolver":"https://pith.science/pith/FBPMLRP46RVAEV7CXLHBYUVSI6","bundle":"https://pith.science/pith/FBPMLRP46RVAEV7CXLHBYUVSI6/bundle.json","state":"https://pith.science/pith/FBPMLRP46RVAEV7CXLHBYUVSI6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBPMLRP46RVAEV7CXLHBYUVSI6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FBPMLRP46RVAEV7CXLHBYUVSI6","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":"612369a6bc8e31e4d6a8ac1743e970260284be9bb5d80af7b465be83c7e0bb6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T12:04:37Z","title_canon_sha256":"e7777bb6e928643b82905e12eb2f1917fc70a28f2c220c807e28702ea4f9b46a"},"schema_version":"1.0","source":{"id":"2201.05411","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05411","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05411v1","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05411","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"FBPMLRP46RVA","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"FBPMLRP46RVAEV7C","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"FBPMLRP4","created_at":"2026-07-05T03:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:9ad6ea9c89c8650664a0c3569b35098957105b5dfb8ac9df318df3fba0e70d92","target":"graph","created_at":"2026-07-05T03:48:32Z","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/2201.05411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label word space, prompt-tuning can achieve excellent results in zero-shot and few-shot scenarios. However, typical prompt-tuning needs a manually designed verbalizer which requires domain expertise and human efforts. And the insufficient label space may introduce considerable bias into the results. In this paper, we focus on eliciting knowledge from pretrained language models and p","authors_text":"Tong Mo, Weiping Li, Wen Zhao, Yinyi Wei, Yongtao Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T12:04:37Z","title":"Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05411","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":"sha256:1bc877e4315a064c10adca82f61b08374afc588ecdfa96ad97ddc7687c4c3a53","target":"record","created_at":"2026-07-05T03:48:32Z","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":"612369a6bc8e31e4d6a8ac1743e970260284be9bb5d80af7b465be83c7e0bb6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T12:04:37Z","title_canon_sha256":"e7777bb6e928643b82905e12eb2f1917fc70a28f2c220c807e28702ea4f9b46a"},"schema_version":"1.0","source":{"id":"2201.05411","kind":"arxiv","version":1}},"canonical_sha256":"285ec5c5fcf46a0257e2bace1c52b24784d61a592ad65004cfa9826c9e3687ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"285ec5c5fcf46a0257e2bace1c52b24784d61a592ad65004cfa9826c9e3687ea","first_computed_at":"2026-07-05T03:48:32.177915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:32.177915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hGNN0SV0P1/HWY+Dr62q37yklC0TZUmXYFM6fP2Mqfo5aGjREXkwimFrGHNvb4tQs6akHpAJOdf9aKttJXO0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:32.178386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05411","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bc877e4315a064c10adca82f61b08374afc588ecdfa96ad97ddc7687c4c3a53","sha256:9ad6ea9c89c8650664a0c3569b35098957105b5dfb8ac9df318df3fba0e70d92"],"state_sha256":"accd79fae62938e67566461a64a344fc89ea09a9e5770e211fc9e23c4b8f49d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZ/BZCVFhJH7riIw9v+qL5Zyl7YWipvK/jy1nBbhcirHGsexrdFBvpTw7lP7kvaExPwbJUO/XfHQAplaPQcPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:00:19.718122Z","bundle_sha256":"32b44c9254c8831efd0792c8022092de39c62358e2aa1c4ef4c93aa676f49c0b"}}