{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MZAA6UVSVAVHAAUSCPN7DGU5DL","short_pith_number":"pith:MZAA6UVS","canonical_record":{"source":{"id":"2401.05224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-10T15:51:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e1014355693289cae6c77dbbf0758f3ea5816fb811af76181418c6bd7fc077e5","abstract_canon_sha256":"8358451cfc449d17c8b702cf8650c93b36dc0dad1ef5fe52bbd2573958e665ec"},"schema_version":"1.0"},"canonical_sha256":"66400f52b2a82a70029213dbf19a9d1ad5901d37d4cd6c039f2b896bd83c4f0c","source":{"kind":"arxiv","id":"2401.05224","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05224","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05224v2","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05224","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"MZAA6UVSVAVH","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"MZAA6UVSVAVHAAUS","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"MZAA6UVS","created_at":"2026-07-05T07:59:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MZAA6UVSVAVHAAUSCPN7DGU5DL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.05224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-10T15:51:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e1014355693289cae6c77dbbf0758f3ea5816fb811af76181418c6bd7fc077e5","abstract_canon_sha256":"8358451cfc449d17c8b702cf8650c93b36dc0dad1ef5fe52bbd2573958e665ec"},"schema_version":"1.0"},"canonical_sha256":"66400f52b2a82a70029213dbf19a9d1ad5901d37d4cd6c039f2b896bd83c4f0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:36.106792Z","signature_b64":"XmaPFnFF0BtJyyTifKyOrOY+l6S+VZ+tUhjkLxtVzcHANHsyGX3j1VafMu0FIR6kZ764W55k09HMbABu9RtKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66400f52b2a82a70029213dbf19a9d1ad5901d37d4cd6c039f2b896bd83c4f0c","last_reissued_at":"2026-07-05T07:59:36.106301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:36.106301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.05224","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":"2026-07-05T07:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVQ6W8KkYo5g0+bvRWIo2fE0OzR/opV/+hysKOOeUrfLhS9itAw5GNLnUIYRsgzmzxPlfnaQtMV6CBwa9cD8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:51:36.580440Z"},"content_sha256":"b7f867ded1e0ca8da941d414ec7425c72b706c0997765047a84814a3321278c5","schema_version":"1.0","event_id":"sha256:b7f867ded1e0ca8da941d414ec7425c72b706c0997765047a84814a3321278c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MZAA6UVSVAVHAAUSCPN7DGU5DL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Vision and Language Encoders Represent the World Similarly?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Karttikeya Mangalam, Mayug Maniparambil, Mohamed El Amine Seddik, Noel E. O'Connor, Raiymbek Akshulakov, Sanath Narayan, Yasser Abdelaziz Dahou Djilali","submitted_at":"2024-01-10T15:51:39Z","abstract_excerpt":"Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoders since they fundamentally represent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned and aligned encoders are semantically similar."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05224","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/2401.05224/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":"2026-07-05T07:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8RPTe6r7+5tWZ0xDLneQsSb3IKY5/rpjJYPDR8bqCLlMXVYE4mXFmtF9aAqgp3KGjTxizma1qqgUDgy/OFg9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:51:36.580960Z"},"content_sha256":"656037960c0780779a7e2dbe05c33bc438f9a25a557d52f84750dcb2fd5b2e70","schema_version":"1.0","event_id":"sha256:656037960c0780779a7e2dbe05c33bc438f9a25a557d52f84750dcb2fd5b2e70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL/bundle.json","state_url":"https://pith.science/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL/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":"2026-08-04T16:51:36Z","links":{"resolver":"https://pith.science/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL","bundle":"https://pith.science/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL/bundle.json","state":"https://pith.science/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZAA6UVSVAVHAAUSCPN7DGU5DL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MZAA6UVSVAVHAAUSCPN7DGU5DL","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":"8358451cfc449d17c8b702cf8650c93b36dc0dad1ef5fe52bbd2573958e665ec","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-10T15:51:39Z","title_canon_sha256":"e1014355693289cae6c77dbbf0758f3ea5816fb811af76181418c6bd7fc077e5"},"schema_version":"1.0","source":{"id":"2401.05224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05224","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05224v2","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05224","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"MZAA6UVSVAVH","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"MZAA6UVSVAVHAAUS","created_at":"2026-07-05T07:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"MZAA6UVS","created_at":"2026-07-05T07:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:656037960c0780779a7e2dbe05c33bc438f9a25a557d52f84750dcb2fd5b2e70","target":"graph","created_at":"2026-07-05T07:59:36Z","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/2401.05224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoders since they fundamentally represent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned and aligned encoders are semantically similar.","authors_text":"Karttikeya Mangalam, Mayug Maniparambil, Mohamed El Amine Seddik, Noel E. O'Connor, Raiymbek Akshulakov, Sanath Narayan, Yasser Abdelaziz Dahou Djilali","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-10T15:51:39Z","title":"Do Vision and Language Encoders Represent the World Similarly?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05224","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:b7f867ded1e0ca8da941d414ec7425c72b706c0997765047a84814a3321278c5","target":"record","created_at":"2026-07-05T07:59:36Z","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":"8358451cfc449d17c8b702cf8650c93b36dc0dad1ef5fe52bbd2573958e665ec","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-10T15:51:39Z","title_canon_sha256":"e1014355693289cae6c77dbbf0758f3ea5816fb811af76181418c6bd7fc077e5"},"schema_version":"1.0","source":{"id":"2401.05224","kind":"arxiv","version":2}},"canonical_sha256":"66400f52b2a82a70029213dbf19a9d1ad5901d37d4cd6c039f2b896bd83c4f0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66400f52b2a82a70029213dbf19a9d1ad5901d37d4cd6c039f2b896bd83c4f0c","first_computed_at":"2026-07-05T07:59:36.106301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:36.106301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XmaPFnFF0BtJyyTifKyOrOY+l6S+VZ+tUhjkLxtVzcHANHsyGX3j1VafMu0FIR6kZ764W55k09HMbABu9RtKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:36.106792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7f867ded1e0ca8da941d414ec7425c72b706c0997765047a84814a3321278c5","sha256:656037960c0780779a7e2dbe05c33bc438f9a25a557d52f84750dcb2fd5b2e70"],"state_sha256":"8b8aa3bbd05767e29f559d544e16b4d03cb748729242c573152560ddafd1096f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7RGKcLFgLsCIcdAYeWwquQ7o/eGFC8hjBsT3viwUPYkxmV50uZpUDfdCzQr77wRlwBmPOQFMacCEISyBPge0Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:51:36.584944Z","bundle_sha256":"33650c4537e410f2547a6b7f4bff5958d4f6eb942a448d8519ac7bd71cde1761"}}