{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M4FA5K7OORSZKELKHQMTTPPHZD","short_pith_number":"pith:M4FA5K7O","canonical_record":{"source":{"id":"2412.14384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T22:35:01Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e0e2cdbaa959c8a84430ea76c875f80862a7682d35032fb209d446fe32ae98bc","abstract_canon_sha256":"4e067daf4a4657c9676230f2a9688052ba553d36271693a10203434074ea0576"},"schema_version":"1.0"},"canonical_sha256":"670a0eabee746595116a3c1939bde7c8f61218c5179fde002afab486bb48b648","source":{"kind":"arxiv","id":"2412.14384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14384","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14384v1","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14384","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"M4FA5K7OORSZ","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"pith_short_16","alias_value":"M4FA5K7OORSZKELK","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"pith_short_8","alias_value":"M4FA5K7O","created_at":"2026-07-05T09:51:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M4FA5K7OORSZKELKHQMTTPPHZD","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T22:35:01Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e0e2cdbaa959c8a84430ea76c875f80862a7682d35032fb209d446fe32ae98bc","abstract_canon_sha256":"4e067daf4a4657c9676230f2a9688052ba553d36271693a10203434074ea0576"},"schema_version":"1.0"},"canonical_sha256":"670a0eabee746595116a3c1939bde7c8f61218c5179fde002afab486bb48b648","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:46.483694Z","signature_b64":"2vWWo1VuNUHXNbKjnnVjBybMFxLCyCuoFUgsXHIx6l3za4L7VedlJpenJ6mNlprw7g1XmxPE3Xhe9rjKb7gDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"670a0eabee746595116a3c1939bde7c8f61218c5179fde002afab486bb48b648","last_reissued_at":"2026-07-05T09:51:46.483231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:46.483231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14384","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":"2026-07-05T09:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GbpWCgyPyHCVKMjrZLtm0iOFhqq+xRGP/achxfV1mnb9rFuZev1HyrT4F5ivlqLwgiLtzRQFHkaSjqyiMyT+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:07:29.661066Z"},"content_sha256":"767041f9772e0083cb0a71a71616228de5aa13bba23f994fb3528719aff32a3a","schema_version":"1.0","event_id":"sha256:767041f9772e0083cb0a71a71616228de5aa13bba23f994fb3528719aff32a3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M4FA5K7OORSZKELKHQMTTPPHZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I0T: Embedding Standardization Method Towards Zero Modality Gap","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eunki Kim, Hyunjung Shim, James Thorne, Na Min An","submitted_at":"2024-12-18T22:35:01Z","abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification. However, recent works extending CLIP suffer from the issue of modality gap, which arises when the image and text embeddings are projected to disparate manifolds, deviating from the intended objective of image-text contrastive learning. We discover that this phenomenon is linked to the modality-specific characteristic that each image/text encoder independently possesses and propose two methods to address the modality gap: (1) a post-hoc embedding standar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14384","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/2412.14384/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":"2026-07-05T09:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJ4B5tcT6yzx8kNyypifHnIdDHPzAOHHD4mb1qIxtMDyGmTNbEeHuO+/mBp2c6ORJa/52hpjrAIRtGDxplaCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:07:29.661469Z"},"content_sha256":"f09504f5832838a806a4dead796c0d701372e90fd9db77a603f6cc970f5e948a","schema_version":"1.0","event_id":"sha256:f09504f5832838a806a4dead796c0d701372e90fd9db77a603f6cc970f5e948a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4FA5K7OORSZKELKHQMTTPPHZD/bundle.json","state_url":"https://pith.science/pith/M4FA5K7OORSZKELKHQMTTPPHZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4FA5K7OORSZKELKHQMTTPPHZD/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":"2026-07-07T10:07:29Z","links":{"resolver":"https://pith.science/pith/M4FA5K7OORSZKELKHQMTTPPHZD","bundle":"https://pith.science/pith/M4FA5K7OORSZKELKHQMTTPPHZD/bundle.json","state":"https://pith.science/pith/M4FA5K7OORSZKELKHQMTTPPHZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4FA5K7OORSZKELKHQMTTPPHZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M4FA5K7OORSZKELKHQMTTPPHZD","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":"4e067daf4a4657c9676230f2a9688052ba553d36271693a10203434074ea0576","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T22:35:01Z","title_canon_sha256":"e0e2cdbaa959c8a84430ea76c875f80862a7682d35032fb209d446fe32ae98bc"},"schema_version":"1.0","source":{"id":"2412.14384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14384","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14384v1","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14384","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"M4FA5K7OORSZ","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"pith_short_16","alias_value":"M4FA5K7OORSZKELK","created_at":"2026-07-05T09:51:46Z"},{"alias_kind":"pith_short_8","alias_value":"M4FA5K7O","created_at":"2026-07-05T09:51:46Z"}],"graph_snapshots":[{"event_id":"sha256:f09504f5832838a806a4dead796c0d701372e90fd9db77a603f6cc970f5e948a","target":"graph","created_at":"2026-07-05T09:51:46Z","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/2412.14384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification. However, recent works extending CLIP suffer from the issue of modality gap, which arises when the image and text embeddings are projected to disparate manifolds, deviating from the intended objective of image-text contrastive learning. We discover that this phenomenon is linked to the modality-specific characteristic that each image/text encoder independently possesses and propose two methods to address the modality gap: (1) a post-hoc embedding standar","authors_text":"Eunki Kim, Hyunjung Shim, James Thorne, Na Min An","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T22:35:01Z","title":"I0T: Embedding Standardization Method Towards Zero Modality Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14384","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":"sha256:767041f9772e0083cb0a71a71616228de5aa13bba23f994fb3528719aff32a3a","target":"record","created_at":"2026-07-05T09:51:46Z","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":"4e067daf4a4657c9676230f2a9688052ba553d36271693a10203434074ea0576","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T22:35:01Z","title_canon_sha256":"e0e2cdbaa959c8a84430ea76c875f80862a7682d35032fb209d446fe32ae98bc"},"schema_version":"1.0","source":{"id":"2412.14384","kind":"arxiv","version":1}},"canonical_sha256":"670a0eabee746595116a3c1939bde7c8f61218c5179fde002afab486bb48b648","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"670a0eabee746595116a3c1939bde7c8f61218c5179fde002afab486bb48b648","first_computed_at":"2026-07-05T09:51:46.483231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:46.483231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2vWWo1VuNUHXNbKjnnVjBybMFxLCyCuoFUgsXHIx6l3za4L7VedlJpenJ6mNlprw7g1XmxPE3Xhe9rjKb7gDAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:46.483694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:767041f9772e0083cb0a71a71616228de5aa13bba23f994fb3528719aff32a3a","sha256:f09504f5832838a806a4dead796c0d701372e90fd9db77a603f6cc970f5e948a"],"state_sha256":"dd39d5b824c2690203fccf740ce3dfae0c64236f1063eefc6ade78cb9a6a878b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IXbYkCvUHZZCnFp5be7kgqaaTi/FlUYOrJOYhhLL1SSOjx5CVJrrcU9oqrCpQ32pe4AudPZB3TUrARV6XAwCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:07:29.663376Z","bundle_sha256":"9f72d90052dff1eecf4ce8d3027d52dc6604ffe0510bd091b6c917b3f07127b3"}}