{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PHCBCBNQLPTVCGMBXNCF5BWKQG","short_pith_number":"pith:PHCBCBNQ","canonical_record":{"source":{"id":"2502.10447","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T11:01:05Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f059f998379020a3bb84242dbb7b036a92908133fb12de33c95d91b0ac213393","abstract_canon_sha256":"c4492ec9fb5efac985525003e7c7ba23bbc355c0d81f7a8ba5d1d07b7a8d7efe"},"schema_version":"1.0"},"canonical_sha256":"79c41105b05be7511981bb445e86ca81a7f32a6686bf709ded0fb9ba74800dbf","source":{"kind":"arxiv","id":"2502.10447","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10447","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10447v2","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10447","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"PHCBCBNQLPTV","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"PHCBCBNQLPTVCGMB","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"PHCBCBNQ","created_at":"2026-07-05T11:06:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PHCBCBNQLPTVCGMBXNCF5BWKQG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10447","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T11:01:05Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f059f998379020a3bb84242dbb7b036a92908133fb12de33c95d91b0ac213393","abstract_canon_sha256":"c4492ec9fb5efac985525003e7c7ba23bbc355c0d81f7a8ba5d1d07b7a8d7efe"},"schema_version":"1.0"},"canonical_sha256":"79c41105b05be7511981bb445e86ca81a7f32a6686bf709ded0fb9ba74800dbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:28.271714Z","signature_b64":"V2UppnSgD2Cr9O76EsjOWP/qxGCaL3mBhB+dUB4fZK3ol4Oi2UinsAIEwg6z4HG3QPhy2QEo8gqwSOQgLhtXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c41105b05be7511981bb445e86ca81a7f32a6686bf709ded0fb9ba74800dbf","last_reissued_at":"2026-07-05T11:06:28.271189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:28.271189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10447","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":"2026-07-05T11:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fC+ClV9emNmLLdaYYjSecsJ3fmQVt/2GU3EbBzd2h9BzAeu2bbkLx5S9FX9tpwfW8wS1FmYA9KK/TWYmsptzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:43:27.821601Z"},"content_sha256":"54e58a7a015e8077e0821f5d7761f4c927828fa7e9702ce6ac30f614a0077a53","schema_version":"1.0","event_id":"sha256:54e58a7a015e8077e0821f5d7761f4c927828fa7e9702ce6ac30f614a0077a53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PHCBCBNQLPTVCGMBXNCF5BWKQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Kangwook Jang, Sangmin Bae, Se-Young Yun, Sungnyun Kim, Sungwoo Cho","submitted_at":"2025-02-11T11:01:05Z","abstract_excerpt":"Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, existing AVSR systems struggle to scale up without compromising computational efficiency. In this study, we introduce MoHAVE (Mixture of Hierarchical Audio-Visual Experts), a novel robust AVSR framework designed to address these scalability constraints. By leveraging a Mixture-of-Experts (MoE) architecture, MoHAVE activates modality-specific expert groups, ensuring dynamic adaptation to various audio-visual inputs with mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10447","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/2502.10447/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":"2026-07-05T11:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9vJY/9jKvR+RyfFQTb7niwTQelCW98M72ZgwDaDJGQHpmKK1hMthjHOm+6fqpWLlX+L2TXabrSVmWrpVREABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:43:27.822456Z"},"content_sha256":"779485f8cee728c1148c0179ab22291ee156c7a5beeaa5f9697fc38dfc9853ee","schema_version":"1.0","event_id":"sha256:779485f8cee728c1148c0179ab22291ee156c7a5beeaa5f9697fc38dfc9853ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG/bundle.json","state_url":"https://pith.science/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG/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":"2026-08-09T07:43:27Z","links":{"resolver":"https://pith.science/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG","bundle":"https://pith.science/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG/bundle.json","state":"https://pith.science/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHCBCBNQLPTVCGMBXNCF5BWKQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PHCBCBNQLPTVCGMBXNCF5BWKQG","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":"c4492ec9fb5efac985525003e7c7ba23bbc355c0d81f7a8ba5d1d07b7a8d7efe","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T11:01:05Z","title_canon_sha256":"f059f998379020a3bb84242dbb7b036a92908133fb12de33c95d91b0ac213393"},"schema_version":"1.0","source":{"id":"2502.10447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10447","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10447v2","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10447","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"PHCBCBNQLPTV","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"PHCBCBNQLPTVCGMB","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"PHCBCBNQ","created_at":"2026-07-05T11:06:28Z"}],"graph_snapshots":[{"event_id":"sha256:779485f8cee728c1148c0179ab22291ee156c7a5beeaa5f9697fc38dfc9853ee","target":"graph","created_at":"2026-07-05T11:06:28Z","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/2502.10447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, existing AVSR systems struggle to scale up without compromising computational efficiency. In this study, we introduce MoHAVE (Mixture of Hierarchical Audio-Visual Experts), a novel robust AVSR framework designed to address these scalability constraints. By leveraging a Mixture-of-Experts (MoE) architecture, MoHAVE activates modality-specific expert groups, ensuring dynamic adaptation to various audio-visual inputs with mi","authors_text":"Kangwook Jang, Sangmin Bae, Se-Young Yun, Sungnyun Kim, Sungwoo Cho","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T11:01:05Z","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10447","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":"sha256:54e58a7a015e8077e0821f5d7761f4c927828fa7e9702ce6ac30f614a0077a53","target":"record","created_at":"2026-07-05T11:06:28Z","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":"c4492ec9fb5efac985525003e7c7ba23bbc355c0d81f7a8ba5d1d07b7a8d7efe","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T11:01:05Z","title_canon_sha256":"f059f998379020a3bb84242dbb7b036a92908133fb12de33c95d91b0ac213393"},"schema_version":"1.0","source":{"id":"2502.10447","kind":"arxiv","version":2}},"canonical_sha256":"79c41105b05be7511981bb445e86ca81a7f32a6686bf709ded0fb9ba74800dbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79c41105b05be7511981bb445e86ca81a7f32a6686bf709ded0fb9ba74800dbf","first_computed_at":"2026-07-05T11:06:28.271189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:28.271189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V2UppnSgD2Cr9O76EsjOWP/qxGCaL3mBhB+dUB4fZK3ol4Oi2UinsAIEwg6z4HG3QPhy2QEo8gqwSOQgLhtXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:28.271714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54e58a7a015e8077e0821f5d7761f4c927828fa7e9702ce6ac30f614a0077a53","sha256:779485f8cee728c1148c0179ab22291ee156c7a5beeaa5f9697fc38dfc9853ee"],"state_sha256":"4460893c460f5a5bef8f0b794af980e2c6cdbeef1a746679201c25d348b89564"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L0oVrdsNd2DmstViLo/j+xNbI2vPPnaraeR/YN5lrT7LfvIbMhJw7EaIkPqXa37StDmLCU8nedIJvXPSv52gAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:43:27.828891Z","bundle_sha256":"e80c3b651259bfe96753cd671d38abf7a2abd94f5f9dd8b6f9663143961887a4"}}