{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KG5PKRB6AOVIF7JSLJDPWXYCGK","short_pith_number":"pith:KG5PKRB6","canonical_record":{"source":{"id":"2405.18570","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T20:28:07Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"a9294643a214b38b3b38506a4254623bedea964d97bffd35e3ba73449d97a824","abstract_canon_sha256":"84162075770a74229b28eff9012b6a642cff3eb4abd249d5e42da3b378c6bc18"},"schema_version":"1.0"},"canonical_sha256":"51baf5443e03aa82fd325a46fb5f0232b02e5fdcfc0694b07009bf1e262728da","source":{"kind":"arxiv","id":"2405.18570","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18570","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18570v3","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18570","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"KG5PKRB6AOVI","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"KG5PKRB6AOVIF7JS","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"KG5PKRB6","created_at":"2026-07-05T08:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KG5PKRB6AOVIF7JSLJDPWXYCGK","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18570","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T20:28:07Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"a9294643a214b38b3b38506a4254623bedea964d97bffd35e3ba73449d97a824","abstract_canon_sha256":"84162075770a74229b28eff9012b6a642cff3eb4abd249d5e42da3b378c6bc18"},"schema_version":"1.0"},"canonical_sha256":"51baf5443e03aa82fd325a46fb5f0232b02e5fdcfc0694b07009bf1e262728da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:41.428455Z","signature_b64":"wqwGKiUf+vu6kOsIznMmv9MGblIdYYtuAiehGVdwxYwc73xxL8UqxsXjIIMDzHPyWiC7RSWFKTqb1R5LS8OKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51baf5443e03aa82fd325a46fb5f0232b02e5fdcfc0694b07009bf1e262728da","last_reissued_at":"2026-07-05T08:28:41.427981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:41.427981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18570","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LH2RbtU8Ekji2fycYhk2dzKCAPi8DskW4IRwVbPMwz010GA8WBFIxVMO6w1dxyI7MCRkQP69Hvl0t4oPke15Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:09:26.643134Z"},"content_sha256":"4dda4e277e2bb67d87e2284c65f1b3aeb24a34056c95e4798337da0457926cd3","schema_version":"1.0","event_id":"sha256:4dda4e277e2bb67d87e2284c65f1b3aeb24a34056c95e4798337da0457926cd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KG5PKRB6AOVIF7JSLJDPWXYCGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abrar Fahim, Alex Murphy, Alona Fyshe","submitted_at":"2024-05-28T20:28:07Z","abstract_excerpt":"Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been reported in two-encoder contrastive models like CLIP, meaning that the image and text embeddings reside in disjoint areas of the latent space. Previous studies suggest that this gap exists due to 1) the cone effect, 2) mismatched pairs in the dataset, and 3) insufficient training. We show that, even when accounting for all these factors, and even when using the same modality, the con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18570","kind":"arxiv","version":3},"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/2405.18570/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":"2026-07-05T08:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qru8vl4T32Uf66+7RfXoyCz9QXqM3pL0hiYR+/f8Fxkyr4/yWKU2WaoAFtnddw4w5KumpaSEEs0O99lId88GDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:09:26.643526Z"},"content_sha256":"549bada480e1f7b14827d47bfa218de87a759f78de9ed247264447dd3f0c3acb","schema_version":"1.0","event_id":"sha256:549bada480e1f7b14827d47bfa218de87a759f78de9ed247264447dd3f0c3acb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK/bundle.json","state_url":"https://pith.science/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK/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":"2026-07-07T07:09:26Z","links":{"resolver":"https://pith.science/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK","bundle":"https://pith.science/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK/bundle.json","state":"https://pith.science/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KG5PKRB6AOVIF7JSLJDPWXYCGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KG5PKRB6AOVIF7JSLJDPWXYCGK","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":"84162075770a74229b28eff9012b6a642cff3eb4abd249d5e42da3b378c6bc18","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T20:28:07Z","title_canon_sha256":"a9294643a214b38b3b38506a4254623bedea964d97bffd35e3ba73449d97a824"},"schema_version":"1.0","source":{"id":"2405.18570","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18570","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18570v3","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18570","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"KG5PKRB6AOVI","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"KG5PKRB6AOVIF7JS","created_at":"2026-07-05T08:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"KG5PKRB6","created_at":"2026-07-05T08:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:549bada480e1f7b14827d47bfa218de87a759f78de9ed247264447dd3f0c3acb","target":"graph","created_at":"2026-07-05T08:28:41Z","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/2405.18570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been reported in two-encoder contrastive models like CLIP, meaning that the image and text embeddings reside in disjoint areas of the latent space. Previous studies suggest that this gap exists due to 1) the cone effect, 2) mismatched pairs in the dataset, and 3) insufficient training. We show that, even when accounting for all these factors, and even when using the same modality, the con","authors_text":"Abrar Fahim, Alex Murphy, Alona Fyshe","cross_cats":["cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T20:28:07Z","title":"It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18570","kind":"arxiv","version":3},"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":"sha256:4dda4e277e2bb67d87e2284c65f1b3aeb24a34056c95e4798337da0457926cd3","target":"record","created_at":"2026-07-05T08:28:41Z","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":"84162075770a74229b28eff9012b6a642cff3eb4abd249d5e42da3b378c6bc18","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T20:28:07Z","title_canon_sha256":"a9294643a214b38b3b38506a4254623bedea964d97bffd35e3ba73449d97a824"},"schema_version":"1.0","source":{"id":"2405.18570","kind":"arxiv","version":3}},"canonical_sha256":"51baf5443e03aa82fd325a46fb5f0232b02e5fdcfc0694b07009bf1e262728da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51baf5443e03aa82fd325a46fb5f0232b02e5fdcfc0694b07009bf1e262728da","first_computed_at":"2026-07-05T08:28:41.427981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:41.427981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqwGKiUf+vu6kOsIznMmv9MGblIdYYtuAiehGVdwxYwc73xxL8UqxsXjIIMDzHPyWiC7RSWFKTqb1R5LS8OKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:41.428455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18570","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dda4e277e2bb67d87e2284c65f1b3aeb24a34056c95e4798337da0457926cd3","sha256:549bada480e1f7b14827d47bfa218de87a759f78de9ed247264447dd3f0c3acb"],"state_sha256":"b19d11fee15bb8ac0f9e7e25fa4934435ffa6dae510e15dd685168aabc2ef98b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vrrb0AZ3BHxJEuT0JpvEx013dW5d2JFs9pwf3425O2qwxawkxprvatyMbZ6vOgZ+1b4479vaa7/cF8XyXxZHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:09:26.645586Z","bundle_sha256":"2d69f4274227a64e9fb77d5a7a6298f19f365eb180a42b1a3cee03332f4ae9e7"}}