{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GKZOGVERMAA35YKZACZVYHHC6P","short_pith_number":"pith:GKZOGVER","canonical_record":{"source":{"id":"2203.02053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T22:53:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"3e9a87a6e7599f047f725fb63d8b2bae7dad6f7baf89c604bd770c2bea87ebc8","abstract_canon_sha256":"9066e7999cfddcbda6e4733c073983ccd8416122caa7a7c61d95f228219f583e"},"schema_version":"1.0"},"canonical_sha256":"32b2e354916001bee15900b35c1ce2f3fcef14f8cadcfa487ef03e4d08c0f6a6","source":{"kind":"arxiv","id":"2203.02053","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02053","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02053v2","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02053","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"GKZOGVERMAA3","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"GKZOGVERMAA35YKZ","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"GKZOGVER","created_at":"2026-07-05T05:08:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GKZOGVERMAA35YKZACZVYHHC6P","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T22:53:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"3e9a87a6e7599f047f725fb63d8b2bae7dad6f7baf89c604bd770c2bea87ebc8","abstract_canon_sha256":"9066e7999cfddcbda6e4733c073983ccd8416122caa7a7c61d95f228219f583e"},"schema_version":"1.0"},"canonical_sha256":"32b2e354916001bee15900b35c1ce2f3fcef14f8cadcfa487ef03e4d08c0f6a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:26.908587Z","signature_b64":"tLm1eVKWqx+E2wL098xLTDMUkfA5rkZOMbKaxzTip34AIxOldZfjTLKNGgZEut1DeY2o4JYEWKbeRMM9mVJABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b2e354916001bee15900b35c1ce2f3fcef14f8cadcfa487ef03e4d08c0f6a6","last_reissued_at":"2026-07-05T05:08:26.907963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:26.907963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02053","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HXs1+4vkx/acn5uJF80/d1M+VxW7i8r2YrTdyXKrDr6uhqL6bAX/mRrxwayqHe8NzfmJfAktwwsZKlgJ1UGGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:20:14.355528Z"},"content_sha256":"3d68391fb74142e45e59018c9a9e7d6cef4eeeff42251e0ecdc41ab882608689","schema_version":"1.0","event_id":"sha256:3d68391fb74142e45e59018c9a9e7d6cef4eeeff42251e0ecdc41ab882608689"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GKZOGVERMAA35YKZACZVYHHC6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"James Zou, Serena Yeung, Weixin Liang, Yongchan Kwon, Yuhui Zhang","submitted_at":"2022-03-03T22:53:54Z","abstract_excerpt":"We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared representation in multi-modal models such as CLIP. Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization. In model initialization, we show empirically and theoretically that the representation of a common deep neural network is restricted to a narrow cone. As a consequence, in a mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02053","kind":"arxiv","version":2},"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/2203.02053/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":"2026-07-05T05:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XDIYZ63FstE6anRHfMfIJ2k2w1KUDmEvdIt1/x0TCdg+DlqkYHBye/aF+tl3WLDbR8rbUj+d4Ju970jNIrdVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:20:14.356474Z"},"content_sha256":"50efa1c43741e96acdc7f15832a3fed59317ff57596c3dcdfc0c03ded77c5f0d","schema_version":"1.0","event_id":"sha256:50efa1c43741e96acdc7f15832a3fed59317ff57596c3dcdfc0c03ded77c5f0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKZOGVERMAA35YKZACZVYHHC6P/bundle.json","state_url":"https://pith.science/pith/GKZOGVERMAA35YKZACZVYHHC6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKZOGVERMAA35YKZACZVYHHC6P/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":"2026-08-07T12:20:14Z","links":{"resolver":"https://pith.science/pith/GKZOGVERMAA35YKZACZVYHHC6P","bundle":"https://pith.science/pith/GKZOGVERMAA35YKZACZVYHHC6P/bundle.json","state":"https://pith.science/pith/GKZOGVERMAA35YKZACZVYHHC6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKZOGVERMAA35YKZACZVYHHC6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GKZOGVERMAA35YKZACZVYHHC6P","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":"9066e7999cfddcbda6e4733c073983ccd8416122caa7a7c61d95f228219f583e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T22:53:54Z","title_canon_sha256":"3e9a87a6e7599f047f725fb63d8b2bae7dad6f7baf89c604bd770c2bea87ebc8"},"schema_version":"1.0","source":{"id":"2203.02053","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02053","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02053v2","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02053","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"GKZOGVERMAA3","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"GKZOGVERMAA35YKZ","created_at":"2026-07-05T05:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"GKZOGVER","created_at":"2026-07-05T05:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:50efa1c43741e96acdc7f15832a3fed59317ff57596c3dcdfc0c03ded77c5f0d","target":"graph","created_at":"2026-07-05T05:08:26Z","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/2203.02053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared representation in multi-modal models such as CLIP. Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization. In model initialization, we show empirically and theoretically that the representation of a common deep neural network is restricted to a narrow cone. As a consequence, in a mu","authors_text":"James Zou, Serena Yeung, Weixin Liang, Yongchan Kwon, Yuhui Zhang","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T22:53:54Z","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02053","kind":"arxiv","version":2},"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":"sha256:3d68391fb74142e45e59018c9a9e7d6cef4eeeff42251e0ecdc41ab882608689","target":"record","created_at":"2026-07-05T05:08:26Z","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":"9066e7999cfddcbda6e4733c073983ccd8416122caa7a7c61d95f228219f583e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T22:53:54Z","title_canon_sha256":"3e9a87a6e7599f047f725fb63d8b2bae7dad6f7baf89c604bd770c2bea87ebc8"},"schema_version":"1.0","source":{"id":"2203.02053","kind":"arxiv","version":2}},"canonical_sha256":"32b2e354916001bee15900b35c1ce2f3fcef14f8cadcfa487ef03e4d08c0f6a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32b2e354916001bee15900b35c1ce2f3fcef14f8cadcfa487ef03e4d08c0f6a6","first_computed_at":"2026-07-05T05:08:26.907963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:26.907963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tLm1eVKWqx+E2wL098xLTDMUkfA5rkZOMbKaxzTip34AIxOldZfjTLKNGgZEut1DeY2o4JYEWKbeRMM9mVJABg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:26.908587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02053","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d68391fb74142e45e59018c9a9e7d6cef4eeeff42251e0ecdc41ab882608689","sha256:50efa1c43741e96acdc7f15832a3fed59317ff57596c3dcdfc0c03ded77c5f0d"],"state_sha256":"9d9096422583e7b14695edd0abcf6096f154e62e1115b754137e2e8ad9155b5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L9EhVAy/UbiZA3CMOSRLu6GWfjOobvUDUDXmdSINQlib6fgzcR+ewJhXhofgX7GhPxuZkkgoVVIwC/r10+SYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:20:14.363276Z","bundle_sha256":"288b36c295da05130d81ae72e03986aaa392ebfc9f81d0ea8588c20a7063e303"}}