{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V57FVNACHVTBGW4IX6LH6FKZWT","short_pith_number":"pith:V57FVNAC","canonical_record":{"source":{"id":"2205.03340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-06T16:22:36Z","cross_cats_sorted":[],"title_canon_sha256":"729c35b490fadaa57dee98f482efc675d84b7a2e66087cae40ef7f52b18da2ee","abstract_canon_sha256":"648d3911277614558b6845b9e2676d38d109e4c3941579a5361bcb519bd3886d"},"schema_version":"1.0"},"canonical_sha256":"af7e5ab4023d66135b88bf967f1559b4e754512211cc883dd6f0afa766d8256b","source":{"kind":"arxiv","id":"2205.03340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03340","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03340v1","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03340","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"V57FVNACHVTB","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"V57FVNACHVTBGW4I","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"V57FVNAC","created_at":"2026-07-05T04:20:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V57FVNACHVTBGW4IX6LH6FKZWT","target":"record","payload":{"canonical_record":{"source":{"id":"2205.03340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-06T16:22:36Z","cross_cats_sorted":[],"title_canon_sha256":"729c35b490fadaa57dee98f482efc675d84b7a2e66087cae40ef7f52b18da2ee","abstract_canon_sha256":"648d3911277614558b6845b9e2676d38d109e4c3941579a5361bcb519bd3886d"},"schema_version":"1.0"},"canonical_sha256":"af7e5ab4023d66135b88bf967f1559b4e754512211cc883dd6f0afa766d8256b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:58.811255Z","signature_b64":"TlUE0pULbugGSvMYTkabthgsLO+RODqAtS2P/+TKiWnanHYsJY/WSUR+eGpVm6SxGtGk/qqiKgwBnOHcuNmiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7e5ab4023d66135b88bf967f1559b4e754512211cc883dd6f0afa766d8256b","last_reissued_at":"2026-07-05T04:20:58.810784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:58.810784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.03340","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":"2026-07-05T04:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkpO8TpU/5Av+bF6SXkgd99wJZmkhfnLOQ8WsRuOucBVddyzuuKOgxRuBBUtZEg+6tGN4m4uXtq3gE4hDqW2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:09:53.771430Z"},"content_sha256":"15d1af901bb7e507529786d1805cb494cc988d892fcd519acbf199a7477516ab","schema_version":"1.0","event_id":"sha256:15d1af901bb7e507529786d1805cb494cc988d892fcd519acbf199a7477516ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V57FVNACHVTBGW4IX6LH6FKZWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt Distribution Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzhuang Liu, Xinmei Tian, Yajing Liu, Yonggang Zhang, Yuning Lu","submitted_at":"2022-05-06T16:22:36Z","abstract_excerpt":"We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03340","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/2205.03340/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":"2026-07-05T04:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xVdQ07KA3SYqXKDl7RYfpH2S9APO0OSB70MgVxQVXScbbsRWV8oeeGjaMEHDrs3P0YkBRWRgpb3h5CvrmmNvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:09:53.772710Z"},"content_sha256":"e297769e9479b97c86c99c49e662a694769d67fd651ea8f8d9ff2faa8ea53436","schema_version":"1.0","event_id":"sha256:e297769e9479b97c86c99c49e662a694769d67fd651ea8f8d9ff2faa8ea53436"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V57FVNACHVTBGW4IX6LH6FKZWT/bundle.json","state_url":"https://pith.science/pith/V57FVNACHVTBGW4IX6LH6FKZWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V57FVNACHVTBGW4IX6LH6FKZWT/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":"2026-08-12T19:09:53Z","links":{"resolver":"https://pith.science/pith/V57FVNACHVTBGW4IX6LH6FKZWT","bundle":"https://pith.science/pith/V57FVNACHVTBGW4IX6LH6FKZWT/bundle.json","state":"https://pith.science/pith/V57FVNACHVTBGW4IX6LH6FKZWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V57FVNACHVTBGW4IX6LH6FKZWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V57FVNACHVTBGW4IX6LH6FKZWT","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":"648d3911277614558b6845b9e2676d38d109e4c3941579a5361bcb519bd3886d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-06T16:22:36Z","title_canon_sha256":"729c35b490fadaa57dee98f482efc675d84b7a2e66087cae40ef7f52b18da2ee"},"schema_version":"1.0","source":{"id":"2205.03340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03340","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03340v1","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03340","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"V57FVNACHVTB","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"V57FVNACHVTBGW4I","created_at":"2026-07-05T04:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"V57FVNAC","created_at":"2026-07-05T04:20:58Z"}],"graph_snapshots":[{"event_id":"sha256:e297769e9479b97c86c99c49e662a694769d67fd651ea8f8d9ff2faa8ea53436","target":"graph","created_at":"2026-07-05T04:20:58Z","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/2205.03340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them ","authors_text":"Jianzhuang Liu, Xinmei Tian, Yajing Liu, Yonggang Zhang, Yuning Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-06T16:22:36Z","title":"Prompt Distribution Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03340","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":"sha256:15d1af901bb7e507529786d1805cb494cc988d892fcd519acbf199a7477516ab","target":"record","created_at":"2026-07-05T04:20:58Z","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":"648d3911277614558b6845b9e2676d38d109e4c3941579a5361bcb519bd3886d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-06T16:22:36Z","title_canon_sha256":"729c35b490fadaa57dee98f482efc675d84b7a2e66087cae40ef7f52b18da2ee"},"schema_version":"1.0","source":{"id":"2205.03340","kind":"arxiv","version":1}},"canonical_sha256":"af7e5ab4023d66135b88bf967f1559b4e754512211cc883dd6f0afa766d8256b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af7e5ab4023d66135b88bf967f1559b4e754512211cc883dd6f0afa766d8256b","first_computed_at":"2026-07-05T04:20:58.810784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:58.810784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlUE0pULbugGSvMYTkabthgsLO+RODqAtS2P/+TKiWnanHYsJY/WSUR+eGpVm6SxGtGk/qqiKgwBnOHcuNmiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:58.811255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.03340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15d1af901bb7e507529786d1805cb494cc988d892fcd519acbf199a7477516ab","sha256:e297769e9479b97c86c99c49e662a694769d67fd651ea8f8d9ff2faa8ea53436"],"state_sha256":"23fed9d6a383e4c493502aa921e649f0327a3696933f607df55517ca0de74c4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/N9L7rO78ZacPwiAH2qdVNkJdGxdJkG+hafiCCIx1l2AnI3Tyfzf4MOAOvZwGDgzlXy7YRpFNcQpXdHqWHrVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:09:53.778404Z","bundle_sha256":"9a9c8806217428b70da9cbd7cbb9f43eb5614b9871f4c46d82a362dce7c6ad5c"}}