{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QRWNU2EHR3OHX4Q65JJTPFSRUW","short_pith_number":"pith:QRWNU2EH","canonical_record":{"source":{"id":"2206.04496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:29:25Z","cross_cats_sorted":[],"title_canon_sha256":"b51fc7c7e70da776e899bb305dd2439b5bd588e8a2b62a1bed64c52d8c957a61","abstract_canon_sha256":"2a6efd00a4c34bc41c145e761bbd770aacf1ef30cae36efe7caa424e1d71cde7"},"schema_version":"1.0"},"canonical_sha256":"846cda68878edc7bf21eea53379651a5818939343c6af685a257de7cba1f9214","source":{"kind":"arxiv","id":"2206.04496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04496","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04496v1","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04496","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"QRWNU2EHR3OH","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"QRWNU2EHR3OHX4Q6","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"QRWNU2EH","created_at":"2026-07-05T04:30:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QRWNU2EHR3OHX4Q65JJTPFSRUW","target":"record","payload":{"canonical_record":{"source":{"id":"2206.04496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:29:25Z","cross_cats_sorted":[],"title_canon_sha256":"b51fc7c7e70da776e899bb305dd2439b5bd588e8a2b62a1bed64c52d8c957a61","abstract_canon_sha256":"2a6efd00a4c34bc41c145e761bbd770aacf1ef30cae36efe7caa424e1d71cde7"},"schema_version":"1.0"},"canonical_sha256":"846cda68878edc7bf21eea53379651a5818939343c6af685a257de7cba1f9214","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:34.454873Z","signature_b64":"sUxnR6lFDdq45aiCuveHcjfQY/J+CgHAU10Ve2F3J28sJTYhlnvTuiDMz4qgJUYN+ePi8WigEx318xOX4ofVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846cda68878edc7bf21eea53379651a5818939343c6af685a257de7cba1f9214","last_reissued_at":"2026-07-05T04:30:34.454443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:34.454443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.04496","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":"2026-07-05T04:30:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNYzapo9lFX44mqMa16/8wzqMoyfhRzMji7x9EPyrn/OlzJ7xL+VmaNyNqyBVz9wxOd8YUdod5FR6kr60YWzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:40:11.773407Z"},"content_sha256":"10caad5bbd7552cf115323647391ab4c34c9e69fbe00924dbf2c80d46da5342d","schema_version":"1.0","event_id":"sha256:10caad5bbd7552cf115323647391ab4c34c9e69fbe00924dbf2c80d46da5342d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QRWNU2EHR3OHX4Q65JJTPFSRUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adri\\'an Javaloy, Isabel Valera, Maryam Meghdadi","submitted_at":"2022-06-09T13:29:25Z","abstract_excerpt":"A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the modalities, e.g., by fitting the image while neglecting the caption. We refer to this limitation as modality collapse. In this work, we argue that this effect is a consequence of conflicting gradients during multimodal VAE training. We show how to detect the sub-graphs in the computational graphs where gradients conflict (impartiality blocks), as well as how to l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04496","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/2206.04496/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":"2026-07-05T04:30:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LTQaHNhDExcCWCPbkLu/sXlUwazVEXf3a3BacHwI3ng+jfM7jV2Gw2VpF327Ofbh+TiNvCj0pQLgFtiZjf1dAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:40:11.774221Z"},"content_sha256":"365910d95f9afb9bf7291a7294a6df4749a630cf19c42158506068d59569db26","schema_version":"1.0","event_id":"sha256:365910d95f9afb9bf7291a7294a6df4749a630cf19c42158506068d59569db26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW/bundle.json","state_url":"https://pith.science/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW/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":"2026-08-10T01:40:11Z","links":{"resolver":"https://pith.science/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW","bundle":"https://pith.science/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW/bundle.json","state":"https://pith.science/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRWNU2EHR3OHX4Q65JJTPFSRUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QRWNU2EHR3OHX4Q65JJTPFSRUW","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":"2a6efd00a4c34bc41c145e761bbd770aacf1ef30cae36efe7caa424e1d71cde7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:29:25Z","title_canon_sha256":"b51fc7c7e70da776e899bb305dd2439b5bd588e8a2b62a1bed64c52d8c957a61"},"schema_version":"1.0","source":{"id":"2206.04496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04496","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04496v1","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04496","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"QRWNU2EHR3OH","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"QRWNU2EHR3OHX4Q6","created_at":"2026-07-05T04:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"QRWNU2EH","created_at":"2026-07-05T04:30:34Z"}],"graph_snapshots":[{"event_id":"sha256:365910d95f9afb9bf7291a7294a6df4749a630cf19c42158506068d59569db26","target":"graph","created_at":"2026-07-05T04:30:34Z","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/2206.04496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the modalities, e.g., by fitting the image while neglecting the caption. We refer to this limitation as modality collapse. In this work, we argue that this effect is a consequence of conflicting gradients during multimodal VAE training. We show how to detect the sub-graphs in the computational graphs where gradients conflict (impartiality blocks), as well as how to l","authors_text":"Adri\\'an Javaloy, Isabel Valera, Maryam Meghdadi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:29:25Z","title":"Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04496","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":"sha256:10caad5bbd7552cf115323647391ab4c34c9e69fbe00924dbf2c80d46da5342d","target":"record","created_at":"2026-07-05T04:30:34Z","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":"2a6efd00a4c34bc41c145e761bbd770aacf1ef30cae36efe7caa424e1d71cde7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:29:25Z","title_canon_sha256":"b51fc7c7e70da776e899bb305dd2439b5bd588e8a2b62a1bed64c52d8c957a61"},"schema_version":"1.0","source":{"id":"2206.04496","kind":"arxiv","version":1}},"canonical_sha256":"846cda68878edc7bf21eea53379651a5818939343c6af685a257de7cba1f9214","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"846cda68878edc7bf21eea53379651a5818939343c6af685a257de7cba1f9214","first_computed_at":"2026-07-05T04:30:34.454443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:34.454443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sUxnR6lFDdq45aiCuveHcjfQY/J+CgHAU10Ve2F3J28sJTYhlnvTuiDMz4qgJUYN+ePi8WigEx318xOX4ofVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:34.454873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10caad5bbd7552cf115323647391ab4c34c9e69fbe00924dbf2c80d46da5342d","sha256:365910d95f9afb9bf7291a7294a6df4749a630cf19c42158506068d59569db26"],"state_sha256":"96f996cfd258981a184fe0f55a44e7b32b003430c35f6a1dc25527076a1fd0a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ih5QPFQgC6k9K8qgH5M+GURNVSo72BVElbDs3AdQ5s213nOqUo6EsfBjdvrv2igUSWPvn6J50Gu8G1AIg43KDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:40:11.779529Z","bundle_sha256":"58c403563e6a584e5682899c215dec7bb0e91929d5cca1290f17c8797a492dc7"}}