{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KJZBGZORIU6FNHOPDWEJHV3JRY","short_pith_number":"pith:KJZBGZOR","canonical_record":{"source":{"id":"2310.19752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:22:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7a5c214cfafae5cf60323f35dfab19e777f1c118fc6cd87c94cc79f72e05b83","abstract_canon_sha256":"a50a5f84ee39a25f47424329181b023e5f739e62eb97cb167beb9604d7927f09"},"schema_version":"1.0"},"canonical_sha256":"52721365d1453c569dcf1d8893d7698e1c5212c8d88e619c9443f0407b30626f","source":{"kind":"arxiv","id":"2310.19752","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19752","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19752v1","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19752","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"KJZBGZORIU6F","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"KJZBGZORIU6FNHOP","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"KJZBGZOR","created_at":"2026-07-05T07:06:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KJZBGZORIU6FNHOPDWEJHV3JRY","target":"record","payload":{"canonical_record":{"source":{"id":"2310.19752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:22:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7a5c214cfafae5cf60323f35dfab19e777f1c118fc6cd87c94cc79f72e05b83","abstract_canon_sha256":"a50a5f84ee39a25f47424329181b023e5f739e62eb97cb167beb9604d7927f09"},"schema_version":"1.0"},"canonical_sha256":"52721365d1453c569dcf1d8893d7698e1c5212c8d88e619c9443f0407b30626f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:54.667492Z","signature_b64":"ZsvQAw33YxN7woSgCoMMCMiXE8CREwpewNvX3SP7wo3+W25rEvnwBjqJ7T+W2pJ6xBg5iOOaI5mNecWsWVeYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52721365d1453c569dcf1d8893d7698e1c5212c8d88e619c9443f0407b30626f","last_reissued_at":"2026-07-05T07:06:54.666976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:54.666976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.19752","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":"2026-07-05T07:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ojOP9w7mHqcT+mFdTKn9sHp2D8Kc/QkOA824rKEQFtwoh98g2draNFwy0GmyfN8yiFqE8xaA78tTN6qWeC0dDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:57:08.367101Z"},"content_sha256":"7f77e003624bc1dd81394884b2298b27b8bbadd4764446bead80d3e4c5b988bd","schema_version":"1.0","event_id":"sha256:7f77e003624bc1dd81394884b2298b27b8bbadd4764446bead80d3e4c5b988bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KJZBGZORIU6FNHOPDWEJHV3JRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Juhua Hu, Qi Qian, Yuanhong Xu","submitted_at":"2023-10-30T17:22:02Z","abstract_excerpt":"Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the class name. However, the modality gap between the text and vision space can result in a sub-optimal performance. We theoretically show that the gap cannot be reduced sufficiently by minimizing the contrastive loss in CLIP and the optimal proxy for vision tasks may reside only in the vision space. Therefore, given unlabeled target vision data, we propose to learn the vision proxy directly with the help from the text proxy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19752","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/2310.19752/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":"2026-07-05T07:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFAAyc5WirqQVnaTDutXvEZPCu2b1zMY9OCdOBgpqZycek3Z1TCl1XyN4jf0PL9zW1ED1togvHDdpddsU7aSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:57:08.367408Z"},"content_sha256":"fecacf9e9c16c88d79948f528cb7f0290efef554b9cfcab0d2b47aa576e9dad1","schema_version":"1.0","event_id":"sha256:fecacf9e9c16c88d79948f528cb7f0290efef554b9cfcab0d2b47aa576e9dad1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJZBGZORIU6FNHOPDWEJHV3JRY/bundle.json","state_url":"https://pith.science/pith/KJZBGZORIU6FNHOPDWEJHV3JRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJZBGZORIU6FNHOPDWEJHV3JRY/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":"2026-08-05T12:57:08Z","links":{"resolver":"https://pith.science/pith/KJZBGZORIU6FNHOPDWEJHV3JRY","bundle":"https://pith.science/pith/KJZBGZORIU6FNHOPDWEJHV3JRY/bundle.json","state":"https://pith.science/pith/KJZBGZORIU6FNHOPDWEJHV3JRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJZBGZORIU6FNHOPDWEJHV3JRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KJZBGZORIU6FNHOPDWEJHV3JRY","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":"a50a5f84ee39a25f47424329181b023e5f739e62eb97cb167beb9604d7927f09","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:22:02Z","title_canon_sha256":"b7a5c214cfafae5cf60323f35dfab19e777f1c118fc6cd87c94cc79f72e05b83"},"schema_version":"1.0","source":{"id":"2310.19752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19752","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19752v1","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19752","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"KJZBGZORIU6F","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"KJZBGZORIU6FNHOP","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"KJZBGZOR","created_at":"2026-07-05T07:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:fecacf9e9c16c88d79948f528cb7f0290efef554b9cfcab0d2b47aa576e9dad1","target":"graph","created_at":"2026-07-05T07:06:54Z","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/2310.19752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the class name. However, the modality gap between the text and vision space can result in a sub-optimal performance. We theoretically show that the gap cannot be reduced sufficiently by minimizing the contrastive loss in CLIP and the optimal proxy for vision tasks may reside only in the vision space. Therefore, given unlabeled target vision data, we propose to learn the vision proxy directly with the help from the text proxy","authors_text":"Juhua Hu, Qi Qian, Yuanhong Xu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:22:02Z","title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19752","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":"sha256:7f77e003624bc1dd81394884b2298b27b8bbadd4764446bead80d3e4c5b988bd","target":"record","created_at":"2026-07-05T07:06:54Z","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":"a50a5f84ee39a25f47424329181b023e5f739e62eb97cb167beb9604d7927f09","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:22:02Z","title_canon_sha256":"b7a5c214cfafae5cf60323f35dfab19e777f1c118fc6cd87c94cc79f72e05b83"},"schema_version":"1.0","source":{"id":"2310.19752","kind":"arxiv","version":1}},"canonical_sha256":"52721365d1453c569dcf1d8893d7698e1c5212c8d88e619c9443f0407b30626f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52721365d1453c569dcf1d8893d7698e1c5212c8d88e619c9443f0407b30626f","first_computed_at":"2026-07-05T07:06:54.666976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:54.666976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZsvQAw33YxN7woSgCoMMCMiXE8CREwpewNvX3SP7wo3+W25rEvnwBjqJ7T+W2pJ6xBg5iOOaI5mNecWsWVeYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:54.667492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f77e003624bc1dd81394884b2298b27b8bbadd4764446bead80d3e4c5b988bd","sha256:fecacf9e9c16c88d79948f528cb7f0290efef554b9cfcab0d2b47aa576e9dad1"],"state_sha256":"acb0fc99864d5413f5c3f1447b9962f8e61d12e4f716021ff5b39285edf485cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3LO3QmiGNUI1jaOllgdV1AxcpoM0954OhDNxI69SZIAvS2jZJQ2+oqCNsFz8cWedwp5s53TDri7+Yf7dfKTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:57:08.371665Z","bundle_sha256":"ba5d1a9afa6df59236997b6123d9f152558481a682f79b21dc2c52ef2d180c1a"}}