{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YSLLEGOFWC2MLBZBOE275JPMUH","short_pith_number":"pith:YSLLEGOF","canonical_record":{"source":{"id":"2412.15277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T03:08:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7faac9cb1ab7d56c91bfcb1536cc02e7ad036883b022d436b0913066bc8b9a3d","abstract_canon_sha256":"b28e60d92f2845def33c4b4102889f5ebb16025d5d91f721412086997a94c1c5"},"schema_version":"1.0"},"canonical_sha256":"c496b219c5b0b4c587217135fea5eca1c4bb24a122bacf98d0dfecedceeb7e9e","source":{"kind":"arxiv","id":"2412.15277","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15277","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15277v1","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15277","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"pith_short_12","alias_value":"YSLLEGOFWC2M","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"pith_short_16","alias_value":"YSLLEGOFWC2MLBZB","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"pith_short_8","alias_value":"YSLLEGOF","created_at":"2026-07-05T09:52:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YSLLEGOFWC2MLBZBOE275JPMUH","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T03:08:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7faac9cb1ab7d56c91bfcb1536cc02e7ad036883b022d436b0913066bc8b9a3d","abstract_canon_sha256":"b28e60d92f2845def33c4b4102889f5ebb16025d5d91f721412086997a94c1c5"},"schema_version":"1.0"},"canonical_sha256":"c496b219c5b0b4c587217135fea5eca1c4bb24a122bacf98d0dfecedceeb7e9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:01.044173Z","signature_b64":"S2WthGwy95cXmVb44tYlgTYzHMm3pQZv94e5I/yd6b3Kwjqoty4/9Us1T0L/g1P6Oqtbf+z2uzJTob2clrFsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c496b219c5b0b4c587217135fea5eca1c4bb24a122bacf98d0dfecedceeb7e9e","last_reissued_at":"2026-07-05T09:52:01.043736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:01.043736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15277","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":"2026-07-05T09:52:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WhpiRjoKSaNUBgv+eWa3aXm3RfuoMH7P35dIEU29Pj3xIBmQemvf4oo0pyTA6aBJZqqxbJFgIkHa/VdLnTQQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:43:07.449195Z"},"content_sha256":"132c7b3b0a4a0e1160d73cd3fb9f86c669c29c5336da1e7ddbbf37e0e55e19aa","schema_version":"1.0","event_id":"sha256:132c7b3b0a4a0e1160d73cd3fb9f86c669c29c5336da1e7ddbbf37e0e55e19aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YSLLEGOFWC2MLBZBOE275JPMUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Biao Liu, Bo Yuan, Wenyi Fang, Xiaoyu Wu, Yang Zheng, Zheng Hu","submitted_at":"2024-12-18T03:08:53Z","abstract_excerpt":"Pre-trained Vision-Language (VL) models such as CLIP have demonstrated their excellent performance across numerous downstream tasks. A recent method, Context Optimization (CoOp), further improves the performance of VL models on downstream tasks by introducing prompt learning. CoOp optimizes a set of learnable vectors, aka prompt, and freezes the whole CLIP model. However, relying solely on CLIP loss to fine-tune prompts can lead to models that are prone to overfitting on downstream task. To address this issue, we propose a plug-in prompt-regularization method called PLPP (Prompt Learning with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15277","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/2412.15277/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":"2026-07-05T09:52:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZjVn7ifYTuc+/2Y8o4pMh4TJmpCDsq4crwvySvhAiAUFIboOxWU9RtWrz62uhub9ISKFHq3Zl4UYphRPgcCpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:43:07.449722Z"},"content_sha256":"ef3d823123040d8a181ad4de7286573bf6a0282bfdc893b5f6557aca0e85a10a","schema_version":"1.0","event_id":"sha256:ef3d823123040d8a181ad4de7286573bf6a0282bfdc893b5f6557aca0e85a10a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSLLEGOFWC2MLBZBOE275JPMUH/bundle.json","state_url":"https://pith.science/pith/YSLLEGOFWC2MLBZBOE275JPMUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSLLEGOFWC2MLBZBOE275JPMUH/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":"2026-08-14T06:43:07Z","links":{"resolver":"https://pith.science/pith/YSLLEGOFWC2MLBZBOE275JPMUH","bundle":"https://pith.science/pith/YSLLEGOFWC2MLBZBOE275JPMUH/bundle.json","state":"https://pith.science/pith/YSLLEGOFWC2MLBZBOE275JPMUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSLLEGOFWC2MLBZBOE275JPMUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YSLLEGOFWC2MLBZBOE275JPMUH","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":"b28e60d92f2845def33c4b4102889f5ebb16025d5d91f721412086997a94c1c5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T03:08:53Z","title_canon_sha256":"7faac9cb1ab7d56c91bfcb1536cc02e7ad036883b022d436b0913066bc8b9a3d"},"schema_version":"1.0","source":{"id":"2412.15277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15277","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15277v1","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15277","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"pith_short_12","alias_value":"YSLLEGOFWC2M","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"pith_short_16","alias_value":"YSLLEGOFWC2MLBZB","created_at":"2026-07-05T09:52:01Z"},{"alias_kind":"pith_short_8","alias_value":"YSLLEGOF","created_at":"2026-07-05T09:52:01Z"}],"graph_snapshots":[{"event_id":"sha256:ef3d823123040d8a181ad4de7286573bf6a0282bfdc893b5f6557aca0e85a10a","target":"graph","created_at":"2026-07-05T09:52:01Z","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/2412.15277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Vision-Language (VL) models such as CLIP have demonstrated their excellent performance across numerous downstream tasks. A recent method, Context Optimization (CoOp), further improves the performance of VL models on downstream tasks by introducing prompt learning. CoOp optimizes a set of learnable vectors, aka prompt, and freezes the whole CLIP model. However, relying solely on CLIP loss to fine-tune prompts can lead to models that are prone to overfitting on downstream task. To address this issue, we propose a plug-in prompt-regularization method called PLPP (Prompt Learning with ","authors_text":"Biao Liu, Bo Yuan, Wenyi Fang, Xiaoyu Wu, Yang Zheng, Zheng Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T03:08:53Z","title":"PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15277","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":"sha256:132c7b3b0a4a0e1160d73cd3fb9f86c669c29c5336da1e7ddbbf37e0e55e19aa","target":"record","created_at":"2026-07-05T09:52:01Z","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":"b28e60d92f2845def33c4b4102889f5ebb16025d5d91f721412086997a94c1c5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T03:08:53Z","title_canon_sha256":"7faac9cb1ab7d56c91bfcb1536cc02e7ad036883b022d436b0913066bc8b9a3d"},"schema_version":"1.0","source":{"id":"2412.15277","kind":"arxiv","version":1}},"canonical_sha256":"c496b219c5b0b4c587217135fea5eca1c4bb24a122bacf98d0dfecedceeb7e9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c496b219c5b0b4c587217135fea5eca1c4bb24a122bacf98d0dfecedceeb7e9e","first_computed_at":"2026-07-05T09:52:01.043736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:01.043736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S2WthGwy95cXmVb44tYlgTYzHMm3pQZv94e5I/yd6b3Kwjqoty4/9Us1T0L/g1P6Oqtbf+z2uzJTob2clrFsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:01.044173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:132c7b3b0a4a0e1160d73cd3fb9f86c669c29c5336da1e7ddbbf37e0e55e19aa","sha256:ef3d823123040d8a181ad4de7286573bf6a0282bfdc893b5f6557aca0e85a10a"],"state_sha256":"b5b9ea363b1240ca2bf1eefa4b510dfa23bbe20951095cfc25fd73faa54344ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoWGZxo1JVPmCvoE6h54Ro2wCN3QLNamxtfNMtl0kJRpPvftbkH+RP0PUb4fjtpKbubW+4n3L4Ac6PLnHy8cBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:43:07.455607Z","bundle_sha256":"4c4f0deccef0373466c858aec5b71a28e54fd7be90098e9f0347e33311a6a487"}}