{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VFOTSZL5YGLRIIP5DY6BGKSDRO","short_pith_number":"pith:VFOTSZL5","canonical_record":{"source":{"id":"2501.18157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-30T05:46:30Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"096b4caaa574537d7f8d2e32882619a2bbc6ba5314d9ae74b45cd4a8db685094","abstract_canon_sha256":"72e4bcfac9eac5045b58ba0e2e1a640922e83dfd4a1cfd28d4c82c8a8190910d"},"schema_version":"1.0"},"canonical_sha256":"a95d39657dc1971421fd1e3c132a438b841794ed7fc5029d95e27d5d1cfacede","source":{"kind":"arxiv","id":"2501.18157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18157","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18157v1","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18157","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"VFOTSZL5YGLR","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"VFOTSZL5YGLRIIP5","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"VFOTSZL5","created_at":"2026-07-05T10:07:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VFOTSZL5YGLRIIP5DY6BGKSDRO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-30T05:46:30Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"096b4caaa574537d7f8d2e32882619a2bbc6ba5314d9ae74b45cd4a8db685094","abstract_canon_sha256":"72e4bcfac9eac5045b58ba0e2e1a640922e83dfd4a1cfd28d4c82c8a8190910d"},"schema_version":"1.0"},"canonical_sha256":"a95d39657dc1971421fd1e3c132a438b841794ed7fc5029d95e27d5d1cfacede","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:07.967506Z","signature_b64":"Om0tuXU443pE+llBcL6Vu+NpBxByCcZ6wBcyvvsmuEArNj9muVGQ4OpF+8qtB+MylSgiA7FDJDbE+j54RSH2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a95d39657dc1971421fd1e3c132a438b841794ed7fc5029d95e27d5d1cfacede","last_reissued_at":"2026-07-05T10:07:07.967051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:07.967051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18157","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":"2026-07-05T10:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nd10VtmyTLsrJZy2ZEOxdZS4PF6iXi5ymrayDTncSTmk157mXlHieNUoyy7ipKS3kp/PbxmQxLKeY6AdltgEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:55:45.685067Z"},"content_sha256":"0f125954a910fd842b90c1648ebd5b40a80e1dd71b01d4ed71493fffb591534d","schema_version":"1.0","event_id":"sha256:0f125954a910fd842b90c1648ebd5b40a80e1dd71b01d4ed71493fffb591534d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VFOTSZL5YGLRIIP5DY6BGKSDRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anurag Kumar, Buye Xu, Honglie Chen, Jacob Donley, Joanna Hong, Ke Tan, Sanjeel Parekh","submitted_at":"2025-01-30T05:46:30Z","abstract_excerpt":"Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come with several constraints such as increased sensory requirements, computational cost, and modality synchronization, to mention a few. These challenges constrain the direct uses of these multimodal solutions in real-world applications. In this work, we develop approaches where the learning happens with all available modalities but the deployment or inference is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18157","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/2501.18157/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":"2026-07-05T10:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ld2KHTskUdyE2DIDLXVOTlj3esmo0Jwt3p69o2sbrydq/vK5560PxY/UjADBnucpGK45rDIQxBbqcOtP9vkUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:55:45.686009Z"},"content_sha256":"99f73d941d96cda70ca70b43e9a54e1045932ece3e3a46c73d2be7a1ca265492","schema_version":"1.0","event_id":"sha256:99f73d941d96cda70ca70b43e9a54e1045932ece3e3a46c73d2be7a1ca265492"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO/bundle.json","state_url":"https://pith.science/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO/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":"2026-08-19T15:55:45Z","links":{"resolver":"https://pith.science/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO","bundle":"https://pith.science/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO/bundle.json","state":"https://pith.science/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFOTSZL5YGLRIIP5DY6BGKSDRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VFOTSZL5YGLRIIP5DY6BGKSDRO","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":"72e4bcfac9eac5045b58ba0e2e1a640922e83dfd4a1cfd28d4c82c8a8190910d","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-30T05:46:30Z","title_canon_sha256":"096b4caaa574537d7f8d2e32882619a2bbc6ba5314d9ae74b45cd4a8db685094"},"schema_version":"1.0","source":{"id":"2501.18157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18157","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18157v1","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18157","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"VFOTSZL5YGLR","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"VFOTSZL5YGLRIIP5","created_at":"2026-07-05T10:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"VFOTSZL5","created_at":"2026-07-05T10:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:99f73d941d96cda70ca70b43e9a54e1045932ece3e3a46c73d2be7a1ca265492","target":"graph","created_at":"2026-07-05T10:07:07Z","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/2501.18157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come with several constraints such as increased sensory requirements, computational cost, and modality synchronization, to mention a few. These challenges constrain the direct uses of these multimodal solutions in real-world applications. In this work, we develop approaches where the learning happens with all available modalities but the deployment or inference is","authors_text":"Anurag Kumar, Buye Xu, Honglie Chen, Jacob Donley, Joanna Hong, Ke Tan, Sanjeel Parekh","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-30T05:46:30Z","title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18157","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":"sha256:0f125954a910fd842b90c1648ebd5b40a80e1dd71b01d4ed71493fffb591534d","target":"record","created_at":"2026-07-05T10:07:07Z","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":"72e4bcfac9eac5045b58ba0e2e1a640922e83dfd4a1cfd28d4c82c8a8190910d","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-30T05:46:30Z","title_canon_sha256":"096b4caaa574537d7f8d2e32882619a2bbc6ba5314d9ae74b45cd4a8db685094"},"schema_version":"1.0","source":{"id":"2501.18157","kind":"arxiv","version":1}},"canonical_sha256":"a95d39657dc1971421fd1e3c132a438b841794ed7fc5029d95e27d5d1cfacede","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a95d39657dc1971421fd1e3c132a438b841794ed7fc5029d95e27d5d1cfacede","first_computed_at":"2026-07-05T10:07:07.967051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:07.967051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Om0tuXU443pE+llBcL6Vu+NpBxByCcZ6wBcyvvsmuEArNj9muVGQ4OpF+8qtB+MylSgiA7FDJDbE+j54RSH2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:07.967506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f125954a910fd842b90c1648ebd5b40a80e1dd71b01d4ed71493fffb591534d","sha256:99f73d941d96cda70ca70b43e9a54e1045932ece3e3a46c73d2be7a1ca265492"],"state_sha256":"3cdb8333abf3ebea1e6ed7d2b723cf70c62ef980bed45e7ad7d77acc248dea9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1lXHLVdXg1uR20lzF6+zjxBQzLH4Lc/YXRhfsFnNpnUPteYvZtlmx41dcPJIG+z/kciSMddVEYhI64bis2fLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:55:45.692717Z","bundle_sha256":"7172667643536d68dde17919a94c94b7e8eb4290bda9d968dc375584a7775288"}}