{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DSA7PWZAGFOAZS2KNX44URM6EX","short_pith_number":"pith:DSA7PWZA","canonical_record":{"source":{"id":"2210.12050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T15:42:41Z","cross_cats_sorted":[],"title_canon_sha256":"a73a257c7c2366da9a75b70f814310a1b9a4f03d60d1432107466fb8fcf5f50e","abstract_canon_sha256":"8d6d7b4bd41f1bb8774014094bddccb3098cd7f4e06424a650cb1b9b5fe087b9"},"schema_version":"1.0"},"canonical_sha256":"1c81f7db20315c0ccb4a6df9ca459e25f631283fc1efc37ef7eda47a04685a22","source":{"kind":"arxiv","id":"2210.12050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12050","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12050v1","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12050","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"DSA7PWZAGFOA","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"DSA7PWZAGFOAZS2K","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"DSA7PWZA","created_at":"2026-07-05T05:09:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DSA7PWZAGFOAZS2KNX44URM6EX","target":"record","payload":{"canonical_record":{"source":{"id":"2210.12050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T15:42:41Z","cross_cats_sorted":[],"title_canon_sha256":"a73a257c7c2366da9a75b70f814310a1b9a4f03d60d1432107466fb8fcf5f50e","abstract_canon_sha256":"8d6d7b4bd41f1bb8774014094bddccb3098cd7f4e06424a650cb1b9b5fe087b9"},"schema_version":"1.0"},"canonical_sha256":"1c81f7db20315c0ccb4a6df9ca459e25f631283fc1efc37ef7eda47a04685a22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:08.574904Z","signature_b64":"Yyv4NTzWpUADyUd/xP2JPUfff7pKJyFbAJmx+7dQKhKC/sxpeTKyNyTZXBCw/i4BmdvAs0dSkzt4QwFZTCPYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c81f7db20315c0ccb4a6df9ca459e25f631283fc1efc37ef7eda47a04685a22","last_reissued_at":"2026-07-05T05:09:08.574555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:08.574555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.12050","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":"2026-07-05T05:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3UDLsw+ioN9y8xnWx2wTFFO1XtPyLMuOH81fAG/HlWjQxq8cB+xDQpt4kBK6cS6MN0Yk9cLZByVHdxP7zKZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:55:17.246495Z"},"content_sha256":"135716acf6a0d9e17718dd8bf7427fb6971cfbbbc025b22d12951580fcdd8a90","schema_version":"1.0","event_id":"sha256:135716acf6a0d9e17718dd8bf7427fb6971cfbbbc025b22d12951580fcdd8a90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DSA7PWZAGFOAZS2KNX44URM6EX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hao Tian, Hua Wu, Shuohuan Wang, Yekun Chai, Yu Sun","submitted_at":"2022-10-21T15:42:41Z","abstract_excerpt":"Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-parameterized characteristics of large pre-trained language models (PLMs). In this paper, we propose Clip-Tuning, a simple yet effective method that adopts diverse frozen \"thinned\" networks of PLMs to obtain a mixture of rewards and thus advance the derivative-free prompt learning. The thinned networks consist of all the hidden units that survive a stationary dropout strategy, whose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12050","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/2210.12050/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":"2026-07-05T05:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JouNdtqeAGWldx9MYN0Nq3fgVKFrY2C7G2jhU0wpsZLUjY4m8++PfL4ASRURYu2GSl4DjSQ3QqDGk0I4vTRFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:55:17.246871Z"},"content_sha256":"c1e24242c26ce920663625ba977dda28993845aeeeddace04306fadb09334557","schema_version":"1.0","event_id":"sha256:c1e24242c26ce920663625ba977dda28993845aeeeddace04306fadb09334557"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSA7PWZAGFOAZS2KNX44URM6EX/bundle.json","state_url":"https://pith.science/pith/DSA7PWZAGFOAZS2KNX44URM6EX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSA7PWZAGFOAZS2KNX44URM6EX/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":"2026-07-07T11:55:17Z","links":{"resolver":"https://pith.science/pith/DSA7PWZAGFOAZS2KNX44URM6EX","bundle":"https://pith.science/pith/DSA7PWZAGFOAZS2KNX44URM6EX/bundle.json","state":"https://pith.science/pith/DSA7PWZAGFOAZS2KNX44URM6EX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSA7PWZAGFOAZS2KNX44URM6EX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DSA7PWZAGFOAZS2KNX44URM6EX","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":"8d6d7b4bd41f1bb8774014094bddccb3098cd7f4e06424a650cb1b9b5fe087b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T15:42:41Z","title_canon_sha256":"a73a257c7c2366da9a75b70f814310a1b9a4f03d60d1432107466fb8fcf5f50e"},"schema_version":"1.0","source":{"id":"2210.12050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12050","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12050v1","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12050","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"DSA7PWZAGFOA","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"DSA7PWZAGFOAZS2K","created_at":"2026-07-05T05:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"DSA7PWZA","created_at":"2026-07-05T05:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:c1e24242c26ce920663625ba977dda28993845aeeeddace04306fadb09334557","target":"graph","created_at":"2026-07-05T05:09:08Z","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/2210.12050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-parameterized characteristics of large pre-trained language models (PLMs). In this paper, we propose Clip-Tuning, a simple yet effective method that adopts diverse frozen \"thinned\" networks of PLMs to obtain a mixture of rewards and thus advance the derivative-free prompt learning. The thinned networks consist of all the hidden units that survive a stationary dropout strategy, whose","authors_text":"HaiFeng Wang, Hao Tian, Hua Wu, Shuohuan Wang, Yekun Chai, Yu Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T15:42:41Z","title":"Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12050","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":"sha256:135716acf6a0d9e17718dd8bf7427fb6971cfbbbc025b22d12951580fcdd8a90","target":"record","created_at":"2026-07-05T05:09:08Z","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":"8d6d7b4bd41f1bb8774014094bddccb3098cd7f4e06424a650cb1b9b5fe087b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T15:42:41Z","title_canon_sha256":"a73a257c7c2366da9a75b70f814310a1b9a4f03d60d1432107466fb8fcf5f50e"},"schema_version":"1.0","source":{"id":"2210.12050","kind":"arxiv","version":1}},"canonical_sha256":"1c81f7db20315c0ccb4a6df9ca459e25f631283fc1efc37ef7eda47a04685a22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c81f7db20315c0ccb4a6df9ca459e25f631283fc1efc37ef7eda47a04685a22","first_computed_at":"2026-07-05T05:09:08.574555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:08.574555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yyv4NTzWpUADyUd/xP2JPUfff7pKJyFbAJmx+7dQKhKC/sxpeTKyNyTZXBCw/i4BmdvAs0dSkzt4QwFZTCPYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:08.574904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.12050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:135716acf6a0d9e17718dd8bf7427fb6971cfbbbc025b22d12951580fcdd8a90","sha256:c1e24242c26ce920663625ba977dda28993845aeeeddace04306fadb09334557"],"state_sha256":"adb56bc86d774b79c7dc1d830fc0d30a58f956fd9eadf3fefe0e85e8e614e869"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ySqz6FUfsddQBjyVzdB9ZcG7jp36SvkE/vszbQyCfUgC19ItKsiM4sMOVk6YRu6wd9eloxKmTAbrCyc7yScHAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:55:17.249626Z","bundle_sha256":"0c7ba5d34867d59edc719233c9591e2e0bf98220a7870758559f229e0b0d4ca0"}}