{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P34XQSADKB7A4TMTDZWBYBXD47","short_pith_number":"pith:P34XQSAD","canonical_record":{"source":{"id":"2506.04870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T10:47:14Z","cross_cats_sorted":[],"title_canon_sha256":"79245d5dffbaf22b1729b644682e6535994e7c8d63ef67169e402c538e5b6ca5","abstract_canon_sha256":"e6dadb463036eb46e9badc902a9f06806eeb290b3ea63be23a8f20db2b961871"},"schema_version":"1.0"},"canonical_sha256":"7ef9784803507e0e4d931e6c1c06e3e7ea0f5299927182923fa4edd6b3857d10","source":{"kind":"arxiv","id":"2506.04870","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04870","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04870v1","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04870","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"P34XQSADKB7A","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"P34XQSADKB7A4TMT","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"P34XQSAD","created_at":"2026-07-05T11:16:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P34XQSADKB7A4TMTDZWBYBXD47","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T10:47:14Z","cross_cats_sorted":[],"title_canon_sha256":"79245d5dffbaf22b1729b644682e6535994e7c8d63ef67169e402c538e5b6ca5","abstract_canon_sha256":"e6dadb463036eb46e9badc902a9f06806eeb290b3ea63be23a8f20db2b961871"},"schema_version":"1.0"},"canonical_sha256":"7ef9784803507e0e4d931e6c1c06e3e7ea0f5299927182923fa4edd6b3857d10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:38.289285Z","signature_b64":"MOoMXj7eBKXKPf4cPeZfmsgzNsKn6JRPD70CvnmbSRNLodyJpYF+3RXddo3toshkGVMZNldiYvewQwq7+71WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ef9784803507e0e4d931e6c1c06e3e7ea0f5299927182923fa4edd6b3857d10","last_reissued_at":"2026-07-05T11:16:38.288682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:38.288682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04870","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":"2026-07-05T11:16:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Qo7a1pCE73ba7E9d8VhD0gwbzIDgG0zwbwXfwKEYz1pJr1qQB9UHju81P+k1gcmDJWPjy0eYS1ahahfWExIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:53:28.707709Z"},"content_sha256":"6abdc1546341ee00543412a3fe0b10d1ffbeb29784e695278def8c6ed312f909","schema_version":"1.0","event_id":"sha256:6abdc1546341ee00543412a3fe0b10d1ffbeb29784e695278def8c6ed312f909"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P34XQSADKB7A4TMTDZWBYBXD47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Multimodal Representations through an Information Bottleneck","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alfonso Ortega, Antonio Almud\\'evar, Jos\\'e Miguel Hern\\'andez-Lobato, Ricard Marxer, Sameer Khurana","submitted_at":"2025-06-05T10:47:14Z","abstract_excerpt":"Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn an aligned representation space. In this paper, we argue that this phenomenon is caused by the presence of modality-specific information in the representation space. Although some of the most widely used contrastive losses maximize the mutual information between representations of both modalities, they are not designed to remove the modality-specific information. We give a theoretical description of this problem throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04870","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/2506.04870/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":"2026-07-05T11:16:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j7Sj3cEchxu0QxauER9YZrr3mFqzhu4I+keOTyNAMUBxkQsvMHaAFWCEt1CjzR+qEEfS3A9DcMFzjaG219EaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:53:28.708643Z"},"content_sha256":"f28497049f5fbdc7b8ab3462959957f8c494532f215a8ea23a10d1a710f21afa","schema_version":"1.0","event_id":"sha256:f28497049f5fbdc7b8ab3462959957f8c494532f215a8ea23a10d1a710f21afa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P34XQSADKB7A4TMTDZWBYBXD47/bundle.json","state_url":"https://pith.science/pith/P34XQSADKB7A4TMTDZWBYBXD47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P34XQSADKB7A4TMTDZWBYBXD47/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":"2026-08-08T04:53:28Z","links":{"resolver":"https://pith.science/pith/P34XQSADKB7A4TMTDZWBYBXD47","bundle":"https://pith.science/pith/P34XQSADKB7A4TMTDZWBYBXD47/bundle.json","state":"https://pith.science/pith/P34XQSADKB7A4TMTDZWBYBXD47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P34XQSADKB7A4TMTDZWBYBXD47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P34XQSADKB7A4TMTDZWBYBXD47","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":"e6dadb463036eb46e9badc902a9f06806eeb290b3ea63be23a8f20db2b961871","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T10:47:14Z","title_canon_sha256":"79245d5dffbaf22b1729b644682e6535994e7c8d63ef67169e402c538e5b6ca5"},"schema_version":"1.0","source":{"id":"2506.04870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04870","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04870v1","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04870","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"P34XQSADKB7A","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"P34XQSADKB7A4TMT","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"P34XQSAD","created_at":"2026-07-05T11:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:f28497049f5fbdc7b8ab3462959957f8c494532f215a8ea23a10d1a710f21afa","target":"graph","created_at":"2026-07-05T11:16:38Z","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/2506.04870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn an aligned representation space. In this paper, we argue that this phenomenon is caused by the presence of modality-specific information in the representation space. Although some of the most widely used contrastive losses maximize the mutual information between representations of both modalities, they are not designed to remove the modality-specific information. We give a theoretical description of this problem throu","authors_text":"Alfonso Ortega, Antonio Almud\\'evar, Jos\\'e Miguel Hern\\'andez-Lobato, Ricard Marxer, Sameer Khurana","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T10:47:14Z","title":"Aligning Multimodal Representations through an Information Bottleneck"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04870","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":"sha256:6abdc1546341ee00543412a3fe0b10d1ffbeb29784e695278def8c6ed312f909","target":"record","created_at":"2026-07-05T11:16:38Z","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":"e6dadb463036eb46e9badc902a9f06806eeb290b3ea63be23a8f20db2b961871","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T10:47:14Z","title_canon_sha256":"79245d5dffbaf22b1729b644682e6535994e7c8d63ef67169e402c538e5b6ca5"},"schema_version":"1.0","source":{"id":"2506.04870","kind":"arxiv","version":1}},"canonical_sha256":"7ef9784803507e0e4d931e6c1c06e3e7ea0f5299927182923fa4edd6b3857d10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ef9784803507e0e4d931e6c1c06e3e7ea0f5299927182923fa4edd6b3857d10","first_computed_at":"2026-07-05T11:16:38.288682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:38.288682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MOoMXj7eBKXKPf4cPeZfmsgzNsKn6JRPD70CvnmbSRNLodyJpYF+3RXddo3toshkGVMZNldiYvewQwq7+71WBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:38.289285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6abdc1546341ee00543412a3fe0b10d1ffbeb29784e695278def8c6ed312f909","sha256:f28497049f5fbdc7b8ab3462959957f8c494532f215a8ea23a10d1a710f21afa"],"state_sha256":"873aba2094743346b8595aa74b9ec281a2eee203088dfdf4c239b033b04b82e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cuGvZ63PCBvzC3snXuxIGilDanU6AYCX74Kzix8LNOAPp2W9LrU586FKX/IgHK6m5gw5IwlqLgC4KvaeOEPnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:53:28.714302Z","bundle_sha256":"dceaeb80eb1891940b8038f195256726ed0560f1f2e18100c9dac359be2cc83d"}}