{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7YZVGICQDUT6HPWJUIGPT4ATOQ","short_pith_number":"pith:7YZVGICQ","canonical_record":{"source":{"id":"2506.03096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:27:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b473bf9c28b49595530a9c0cc786dc3f8e267ad6ed29c4b8feb1c089ac32dff0","abstract_canon_sha256":"c99ee601587305415ea1122fc38faaacf36607fad3d4311765131fd011ea49cc"},"schema_version":"1.0"},"canonical_sha256":"fe335320501d27e3bec9a20cf9f0137428b7f76dfd0a69aa6ceceafc20287c3b","source":{"kind":"arxiv","id":"2506.03096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03096","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03096v1","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03096","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"7YZVGICQDUT6","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"7YZVGICQDUT6HPWJ","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"7YZVGICQ","created_at":"2026-07-05T11:15:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7YZVGICQDUT6HPWJUIGPT4ATOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:27:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b473bf9c28b49595530a9c0cc786dc3f8e267ad6ed29c4b8feb1c089ac32dff0","abstract_canon_sha256":"c99ee601587305415ea1122fc38faaacf36607fad3d4311765131fd011ea49cc"},"schema_version":"1.0"},"canonical_sha256":"fe335320501d27e3bec9a20cf9f0137428b7f76dfd0a69aa6ceceafc20287c3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:14.793326Z","signature_b64":"DZSfjFSdjRSnGJYXrCYLXW+KZN1ihkxBJvh5IVMinLcgQTge10NJTj63VPNOTkvl17yomTI7tkG5P/GrIDRaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe335320501d27e3bec9a20cf9f0137428b7f76dfd0a69aa6ceceafc20287c3b","last_reissued_at":"2026-07-05T11:15:14.792841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:14.792841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03096","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":"2026-07-05T11:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Ve6klqa+ctrgHIuKqzOvGmKhSPlwZWCQg0GHgEqiXsygW1Mo6zeFg2nKAQ4Q+dNGfT0yuDazgtnTYIQlXE8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:14:14.702632Z"},"content_sha256":"bf7ecbc8c0d3d7938f26ee3f48d78d2f0a94d3cac50097218ca352f184df2734","schema_version":"1.0","event_id":"sha256:bf7ecbc8c0d3d7938f26ee3f48d78d2f0a94d3cac50097218ca352f184df2734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7YZVGICQDUT6HPWJUIGPT4ATOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christian Schlarmann, Francesco Croce, Matthias Hein, Nicolas Flammarion","submitted_at":"2025-06-03T17:27:12Z","abstract_excerpt":"Contrastive language-image pre-training aligns the features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressive performance in several zero-shot tasks, it cannot natively handle multimodal inputs, i.e., encoding image and text into a single feature vector. As a remedy, it is common practice to use additional modules to merge the features extracted by the unimodal encoders. In this work, we present FuseLIP, an alternative architecture for multimodal embedding. Leveraging recent progress in discrete image tokenizers, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03096","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/2506.03096/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":"2026-07-05T11:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8PrDQS6dwUMJd8zZ5valPKGpTHFTCjNkChTrx0txUoPLBFmjXuQKX/V1YnwRMEsovdal8JfDrDN5LzUXsl+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:14:14.703563Z"},"content_sha256":"2b510f9569bc40f1819f1ec2fe2c0430712cc33952db6d990115d473ddfdcabf","schema_version":"1.0","event_id":"sha256:2b510f9569bc40f1819f1ec2fe2c0430712cc33952db6d990115d473ddfdcabf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ/bundle.json","state_url":"https://pith.science/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ/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":"2026-08-08T11:14:14Z","links":{"resolver":"https://pith.science/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ","bundle":"https://pith.science/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ/bundle.json","state":"https://pith.science/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YZVGICQDUT6HPWJUIGPT4ATOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7YZVGICQDUT6HPWJUIGPT4ATOQ","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":"c99ee601587305415ea1122fc38faaacf36607fad3d4311765131fd011ea49cc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:27:12Z","title_canon_sha256":"b473bf9c28b49595530a9c0cc786dc3f8e267ad6ed29c4b8feb1c089ac32dff0"},"schema_version":"1.0","source":{"id":"2506.03096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03096","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03096v1","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03096","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"7YZVGICQDUT6","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"7YZVGICQDUT6HPWJ","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"7YZVGICQ","created_at":"2026-07-05T11:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:2b510f9569bc40f1819f1ec2fe2c0430712cc33952db6d990115d473ddfdcabf","target":"graph","created_at":"2026-07-05T11:15:14Z","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/2506.03096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language-image pre-training aligns the features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressive performance in several zero-shot tasks, it cannot natively handle multimodal inputs, i.e., encoding image and text into a single feature vector. As a remedy, it is common practice to use additional modules to merge the features extracted by the unimodal encoders. In this work, we present FuseLIP, an alternative architecture for multimodal embedding. Leveraging recent progress in discrete image tokenizers, we pr","authors_text":"Christian Schlarmann, Francesco Croce, Matthias Hein, Nicolas Flammarion","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:27:12Z","title":"FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03096","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:bf7ecbc8c0d3d7938f26ee3f48d78d2f0a94d3cac50097218ca352f184df2734","target":"record","created_at":"2026-07-05T11:15:14Z","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":"c99ee601587305415ea1122fc38faaacf36607fad3d4311765131fd011ea49cc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:27:12Z","title_canon_sha256":"b473bf9c28b49595530a9c0cc786dc3f8e267ad6ed29c4b8feb1c089ac32dff0"},"schema_version":"1.0","source":{"id":"2506.03096","kind":"arxiv","version":1}},"canonical_sha256":"fe335320501d27e3bec9a20cf9f0137428b7f76dfd0a69aa6ceceafc20287c3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe335320501d27e3bec9a20cf9f0137428b7f76dfd0a69aa6ceceafc20287c3b","first_computed_at":"2026-07-05T11:15:14.792841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:14.792841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DZSfjFSdjRSnGJYXrCYLXW+KZN1ihkxBJvh5IVMinLcgQTge10NJTj63VPNOTkvl17yomTI7tkG5P/GrIDRaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:14.793326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf7ecbc8c0d3d7938f26ee3f48d78d2f0a94d3cac50097218ca352f184df2734","sha256:2b510f9569bc40f1819f1ec2fe2c0430712cc33952db6d990115d473ddfdcabf"],"state_sha256":"a4d332b7954c4bc07352dbff5f51d36c15fc3822e6901d99453ad50a0d45484d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCYRtQ5l7HroI1rnrn0+980Z8zahoPAkIAXaGdtMRVPxvHJJXsfb1xuXtXge2tbGxgu/+AETHy5ymSZiDf0/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:14:14.710211Z","bundle_sha256":"2f06d9b9d7d6b0497133f22c25180b981e6c32f231d779015a4caf5448932a7a"}}