{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D4YB7HSDSJ6BYAF2VQYFJ4FGT5","short_pith_number":"pith:D4YB7HSD","canonical_record":{"source":{"id":"2409.07402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T16:42:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"7ae79fa6643cf6ab7d70db93be16e3cc86dadf9286d4f1bece2baeca92bc8ecd","abstract_canon_sha256":"b7b95bb98b4008d46ba511efdc57e7f6706d9e423200884cde4a394d0aa4b6dc"},"schema_version":"1.0"},"canonical_sha256":"1f301f9e43927c1c00baac3054f0a69f5a57d62709fab64549cc922c62d5d69b","source":{"kind":"arxiv","id":"2409.07402","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07402","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07402v2","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07402","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"pith_short_12","alias_value":"D4YB7HSDSJ6B","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"pith_short_16","alias_value":"D4YB7HSDSJ6BYAF2","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"pith_short_8","alias_value":"D4YB7HSD","created_at":"2026-07-05T10:24:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D4YB7HSDSJ6BYAF2VQYFJ4FGT5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.07402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T16:42:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"7ae79fa6643cf6ab7d70db93be16e3cc86dadf9286d4f1bece2baeca92bc8ecd","abstract_canon_sha256":"b7b95bb98b4008d46ba511efdc57e7f6706d9e423200884cde4a394d0aa4b6dc"},"schema_version":"1.0"},"canonical_sha256":"1f301f9e43927c1c00baac3054f0a69f5a57d62709fab64549cc922c62d5d69b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:54.561223Z","signature_b64":"1D1u/0kwIXxM7S1MGkPEl2J5nwwW/KfC5RdtFkjL3u6MW+YF0afNa9wWVx0jUC8C00ssfJ5V2r5Uj5j5bVpUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f301f9e43927c1c00baac3054f0a69f5a57d62709fab64549cc922c62d5d69b","last_reissued_at":"2026-07-05T10:24:54.560241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:54.560241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.07402","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":"2026-07-05T10:24:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6zpeaInT7QNRUe4AfGlnRVquiNhddRM24IfD5zkDoG7uqzaev9seABg6Tftw8xvR9CmNw7mCIlFFoOTUoEpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:09:29.605246Z"},"content_sha256":"6f2d327aca12c7056cc9673adeb1063534add68042be6956c96395d54ab617be","schema_version":"1.0","event_id":"sha256:6f2d327aca12c7056cc9673adeb1063534add68042be6956c96395d54ab617be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D4YB7HSDSJ6BYAF2VQYFJ4FGT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What to align in multimodal contrastive learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Benoit Dufumier, Devis Tuia, Javiera Castillo-Navarro, Jean-Philippe Thiran","submitted_at":"2024-09-11T16:42:22Z","abstract_excerpt":"Humans perceive the world through multisensory integration, blending the information of different modalities to adapt their behavior. Contrastive learning offers an appealing solution for multimodal self-supervised learning. Indeed, by considering each modality as a different view of the same entity, it learns to align features of different modalities in a shared representation space. However, this approach is intrinsically limited as it only learns shared or redundant information between modalities, while multimodal interactions can arise in other ways. In this work, we introduce CoMM, a Cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07402","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/2409.07402/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":"2026-07-05T10:24:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qhv+iH/MbJOweawjYiolO3KeIiTfvTfOiRjmrfJB47hiVTlrKPggstcbSYkTqRD1TPdeOiijM6OqERMndjRHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:09:29.606226Z"},"content_sha256":"7efb5556c152fb62300168c54994680439029ebf37e895aaa804c60ab01cd112","schema_version":"1.0","event_id":"sha256:7efb5556c152fb62300168c54994680439029ebf37e895aaa804c60ab01cd112"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5/bundle.json","state_url":"https://pith.science/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5/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":"2026-08-07T01:09:29Z","links":{"resolver":"https://pith.science/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5","bundle":"https://pith.science/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5/bundle.json","state":"https://pith.science/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4YB7HSDSJ6BYAF2VQYFJ4FGT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D4YB7HSDSJ6BYAF2VQYFJ4FGT5","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":"b7b95bb98b4008d46ba511efdc57e7f6706d9e423200884cde4a394d0aa4b6dc","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T16:42:22Z","title_canon_sha256":"7ae79fa6643cf6ab7d70db93be16e3cc86dadf9286d4f1bece2baeca92bc8ecd"},"schema_version":"1.0","source":{"id":"2409.07402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07402","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07402v2","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07402","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"pith_short_12","alias_value":"D4YB7HSDSJ6B","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"pith_short_16","alias_value":"D4YB7HSDSJ6BYAF2","created_at":"2026-07-05T10:24:54Z"},{"alias_kind":"pith_short_8","alias_value":"D4YB7HSD","created_at":"2026-07-05T10:24:54Z"}],"graph_snapshots":[{"event_id":"sha256:7efb5556c152fb62300168c54994680439029ebf37e895aaa804c60ab01cd112","target":"graph","created_at":"2026-07-05T10:24:54Z","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/2409.07402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans perceive the world through multisensory integration, blending the information of different modalities to adapt their behavior. Contrastive learning offers an appealing solution for multimodal self-supervised learning. Indeed, by considering each modality as a different view of the same entity, it learns to align features of different modalities in a shared representation space. However, this approach is intrinsically limited as it only learns shared or redundant information between modalities, while multimodal interactions can arise in other ways. In this work, we introduce CoMM, a Cont","authors_text":"Benoit Dufumier, Devis Tuia, Javiera Castillo-Navarro, Jean-Philippe Thiran","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T16:42:22Z","title":"What to align in multimodal contrastive learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07402","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":"sha256:6f2d327aca12c7056cc9673adeb1063534add68042be6956c96395d54ab617be","target":"record","created_at":"2026-07-05T10:24:54Z","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":"b7b95bb98b4008d46ba511efdc57e7f6706d9e423200884cde4a394d0aa4b6dc","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T16:42:22Z","title_canon_sha256":"7ae79fa6643cf6ab7d70db93be16e3cc86dadf9286d4f1bece2baeca92bc8ecd"},"schema_version":"1.0","source":{"id":"2409.07402","kind":"arxiv","version":2}},"canonical_sha256":"1f301f9e43927c1c00baac3054f0a69f5a57d62709fab64549cc922c62d5d69b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f301f9e43927c1c00baac3054f0a69f5a57d62709fab64549cc922c62d5d69b","first_computed_at":"2026-07-05T10:24:54.560241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:54.560241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1D1u/0kwIXxM7S1MGkPEl2J5nwwW/KfC5RdtFkjL3u6MW+YF0afNa9wWVx0jUC8C00ssfJ5V2r5Uj5j5bVpUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:54.561223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f2d327aca12c7056cc9673adeb1063534add68042be6956c96395d54ab617be","sha256:7efb5556c152fb62300168c54994680439029ebf37e895aaa804c60ab01cd112"],"state_sha256":"89083299306d3bbd94aaaec62fbf373ba6e08379d8237680fee41d4648a6939b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDjUeAvoS8TqHrc3m2gtdjg8x4/6Om4tRxatzr1q39ujTWiHi1prm6LSsWxJ0falB07RT9CBRzlbEnSwzqR0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:09:29.612612Z","bundle_sha256":"a1af324efaa0b0be584d9d43678b05618ae4a9c2f000ef17f1cd5cb544050131"}}