{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5HIMZCMP7BAL7EV56GA7JIXG4V","short_pith_number":"pith:5HIMZCMP","canonical_record":{"source":{"id":"2305.00350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T22:05:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"6fe762adb5607212900109b6f26547016ff91731c0195a0461ffba475a2caa25","abstract_canon_sha256":"303f2d87d7debf6b22d9ce1e5a42fa23975c0b1cd0822f1ac09bb1f852891d4b"},"schema_version":"1.0"},"canonical_sha256":"e9d0cc898ff840bf92bdf181f4a2e6e56145a8be5cd931af6f3df677a089dafe","source":{"kind":"arxiv","id":"2305.00350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00350","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00350v1","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00350","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"5HIMZCMP7BAL","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"5HIMZCMP7BAL7EV5","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"5HIMZCMP","created_at":"2026-07-05T06:05:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5HIMZCMP7BAL7EV56GA7JIXG4V","target":"record","payload":{"canonical_record":{"source":{"id":"2305.00350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T22:05:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"6fe762adb5607212900109b6f26547016ff91731c0195a0461ffba475a2caa25","abstract_canon_sha256":"303f2d87d7debf6b22d9ce1e5a42fa23975c0b1cd0822f1ac09bb1f852891d4b"},"schema_version":"1.0"},"canonical_sha256":"e9d0cc898ff840bf92bdf181f4a2e6e56145a8be5cd931af6f3df677a089dafe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:40.399352Z","signature_b64":"fAc0Au/HvI0B+3WMmZvvSXftFU3bcFIP+aPaLdigPbXZqKOqzRP0uoT4SOAs/YsyMFgr8/gdthCgTYChwiTqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d0cc898ff840bf92bdf181f4a2e6e56145a8be5cd931af6f3df677a089dafe","last_reissued_at":"2026-07-05T06:05:40.398921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:40.398921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.00350","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":"2026-07-05T06:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qqz9jh+P/FSoaI3BuQ70k5wBByT0aVxzl6QLcqhM8jJEBk/EmEPSAXeFWHkDXWJZjmpMcPu/020Zcsq1lDCkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:18:26.535407Z"},"content_sha256":"f42807eecf396bfa5381794ff00aebb860a040c587996c0c54aebf4b6b8e74dc","schema_version":"1.0","event_id":"sha256:f42807eecf396bfa5381794ff00aebb860a040c587996c0c54aebf4b6b8e74dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5HIMZCMP7BAL7EV56GA7JIXG4V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huangjie Zheng, Korawat Tanwisuth, Mingyuan Zhou, Pengcheng He, Shujian Zhang","submitted_at":"2023-04-29T22:05:22Z","abstract_excerpt":"Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to adapt them to downstream tasks. To overcome this critical limitation, we propose an unsupervised fine-tuning framework to directly fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00350","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/2305.00350/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":"2026-07-05T06:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HS+iDWSZbxE9R7AVo+F/8bSm1f0QC8+eHHpG52+awQ1CVuOQYOMkjBXTlj1gilxRsD6lG64yWALO0bSkLf1ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:18:26.536084Z"},"content_sha256":"04cf1a9ff05a91fbbfb5c1520fc632e7c36b8877fd299b46c19c998c08f11474","schema_version":"1.0","event_id":"sha256:04cf1a9ff05a91fbbfb5c1520fc632e7c36b8877fd299b46c19c998c08f11474"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HIMZCMP7BAL7EV56GA7JIXG4V/bundle.json","state_url":"https://pith.science/pith/5HIMZCMP7BAL7EV56GA7JIXG4V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HIMZCMP7BAL7EV56GA7JIXG4V/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":"2026-08-06T17:18:26Z","links":{"resolver":"https://pith.science/pith/5HIMZCMP7BAL7EV56GA7JIXG4V","bundle":"https://pith.science/pith/5HIMZCMP7BAL7EV56GA7JIXG4V/bundle.json","state":"https://pith.science/pith/5HIMZCMP7BAL7EV56GA7JIXG4V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HIMZCMP7BAL7EV56GA7JIXG4V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5HIMZCMP7BAL7EV56GA7JIXG4V","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":"303f2d87d7debf6b22d9ce1e5a42fa23975c0b1cd0822f1ac09bb1f852891d4b","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T22:05:22Z","title_canon_sha256":"6fe762adb5607212900109b6f26547016ff91731c0195a0461ffba475a2caa25"},"schema_version":"1.0","source":{"id":"2305.00350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00350","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00350v1","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00350","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"5HIMZCMP7BAL","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"5HIMZCMP7BAL7EV5","created_at":"2026-07-05T06:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"5HIMZCMP","created_at":"2026-07-05T06:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:04cf1a9ff05a91fbbfb5c1520fc632e7c36b8877fd299b46c19c998c08f11474","target":"graph","created_at":"2026-07-05T06:05:40Z","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/2305.00350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to adapt them to downstream tasks. To overcome this critical limitation, we propose an unsupervised fine-tuning framework to directly fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and ","authors_text":"Huangjie Zheng, Korawat Tanwisuth, Mingyuan Zhou, Pengcheng He, Shujian Zhang","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T22:05:22Z","title":"POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00350","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:f42807eecf396bfa5381794ff00aebb860a040c587996c0c54aebf4b6b8e74dc","target":"record","created_at":"2026-07-05T06:05:40Z","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":"303f2d87d7debf6b22d9ce1e5a42fa23975c0b1cd0822f1ac09bb1f852891d4b","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-29T22:05:22Z","title_canon_sha256":"6fe762adb5607212900109b6f26547016ff91731c0195a0461ffba475a2caa25"},"schema_version":"1.0","source":{"id":"2305.00350","kind":"arxiv","version":1}},"canonical_sha256":"e9d0cc898ff840bf92bdf181f4a2e6e56145a8be5cd931af6f3df677a089dafe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9d0cc898ff840bf92bdf181f4a2e6e56145a8be5cd931af6f3df677a089dafe","first_computed_at":"2026-07-05T06:05:40.398921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:40.398921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fAc0Au/HvI0B+3WMmZvvSXftFU3bcFIP+aPaLdigPbXZqKOqzRP0uoT4SOAs/YsyMFgr8/gdthCgTYChwiTqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:40.399352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.00350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f42807eecf396bfa5381794ff00aebb860a040c587996c0c54aebf4b6b8e74dc","sha256:04cf1a9ff05a91fbbfb5c1520fc632e7c36b8877fd299b46c19c998c08f11474"],"state_sha256":"5a73f739c09b424ff244c6e6bedf27da6f027c07b34479c4e737d4e5d342d1e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZqxMB1Pyq3O6ZoqAy+Mcp9wMFHMYwZOVm+u2a5NYzv3I3P67/IOqLxWX+0KrKx1prM9KyEJ8JD5iD5dhlYNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:18:26.542428Z","bundle_sha256":"b2ee29d1a649c0f02107f5f2ab056315ef1de3800662a2392b822eca76a49ec5"}}