{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MWDZA6VZHNWZVB4ELJA4AGAC5X","short_pith_number":"pith:MWDZA6VZ","canonical_record":{"source":{"id":"2508.07608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-11T04:23:08Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"eff07e600a1ce5d603e16cabcfe1a9a7aafed942bc63cd26ffa6f8e5152aee15","abstract_canon_sha256":"9b7e22d9210cae687f8478966465220982d7d30aa87179a5b203786a3f62389a"},"schema_version":"1.0"},"canonical_sha256":"6587907ab93b6d9a87845a41c01802edfbe84042eb0c6b0699a4320ede248402","source":{"kind":"arxiv","id":"2508.07608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07608","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07608v1","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07608","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"pith_short_12","alias_value":"MWDZA6VZHNWZ","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"pith_short_16","alias_value":"MWDZA6VZHNWZVB4E","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"pith_short_8","alias_value":"MWDZA6VZ","created_at":"2026-07-05T11:52:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MWDZA6VZHNWZVB4ELJA4AGAC5X","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-11T04:23:08Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"eff07e600a1ce5d603e16cabcfe1a9a7aafed942bc63cd26ffa6f8e5152aee15","abstract_canon_sha256":"9b7e22d9210cae687f8478966465220982d7d30aa87179a5b203786a3f62389a"},"schema_version":"1.0"},"canonical_sha256":"6587907ab93b6d9a87845a41c01802edfbe84042eb0c6b0699a4320ede248402","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:04.702764Z","signature_b64":"0A+BtghqyDMfkJlPCF6n4fiFlgqhabcS1Ba1pKpdUc3uoBBr4vdHyEz71BuW+PcqlYRLM8BML/SEKx3QyK3dAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6587907ab93b6d9a87845a41c01802edfbe84042eb0c6b0699a4320ede248402","last_reissued_at":"2026-07-05T11:52:04.702238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:04.702238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07608","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":"2026-07-05T11:52:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aE9TVQXic10yEESHrDFN3FQ3n1/1xWVd2kCKwp8x2bpe24Smqn2CmwevuLpuJXv1xHpYQKMhoaPBStefjohaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:22:55.984560Z"},"content_sha256":"21dacfeb6e4520e1e9b8b90bad99008e48eb7ff450dd662e85bc5567333f3019","schema_version":"1.0","event_id":"sha256:21dacfeb6e4520e1e9b8b90bad99008e48eb7ff450dd662e85bc5567333f3019"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MWDZA6VZHNWZVB4ELJA4AGAC5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Danlei Huang, Fei Yu, Junxiao Xue, Xiaozhen Liu, Xinyi Yin, Xuecheng Wu","submitted_at":"2025-08-11T04:23:08Z","abstract_excerpt":"Audio-visual speech recognition (AVSR) combines audio-visual modalities to improve speech recognition, especially in noisy environments. However, most existing methods deploy the unidirectional enhancement or symmetric fusion manner, which limits their capability to capture heterogeneous and complementary correlations of audio-visual data-especially under asymmetric information conditions. To tackle these gaps, we introduce a new AVSR framework termed AD-AVSR based on bidirectional modality enhancement. Specifically, we first introduce the audio dual-stream encoding strategy to enrich audio re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07608","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/2508.07608/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":"2026-07-05T11:52:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HdlqMJhoAN+iuh+0xbdAsSsqCym7t0hrilqNcA0GN3oYLE+cSTp0NYdq/QBzhg4Kox9kaSe0V1qfV034wraYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:22:55.985082Z"},"content_sha256":"4dfa87eb4dbc85d0eff93e5d90dfe769ad76f41e880f141b59cf56c1b2f5e0bf","schema_version":"1.0","event_id":"sha256:4dfa87eb4dbc85d0eff93e5d90dfe769ad76f41e880f141b59cf56c1b2f5e0bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X/bundle.json","state_url":"https://pith.science/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X/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":"2026-08-06T07:22:55Z","links":{"resolver":"https://pith.science/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X","bundle":"https://pith.science/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X/bundle.json","state":"https://pith.science/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWDZA6VZHNWZVB4ELJA4AGAC5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MWDZA6VZHNWZVB4ELJA4AGAC5X","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":"9b7e22d9210cae687f8478966465220982d7d30aa87179a5b203786a3f62389a","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-11T04:23:08Z","title_canon_sha256":"eff07e600a1ce5d603e16cabcfe1a9a7aafed942bc63cd26ffa6f8e5152aee15"},"schema_version":"1.0","source":{"id":"2508.07608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07608","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07608v1","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07608","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"pith_short_12","alias_value":"MWDZA6VZHNWZ","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"pith_short_16","alias_value":"MWDZA6VZHNWZVB4E","created_at":"2026-07-05T11:52:04Z"},{"alias_kind":"pith_short_8","alias_value":"MWDZA6VZ","created_at":"2026-07-05T11:52:04Z"}],"graph_snapshots":[{"event_id":"sha256:4dfa87eb4dbc85d0eff93e5d90dfe769ad76f41e880f141b59cf56c1b2f5e0bf","target":"graph","created_at":"2026-07-05T11:52:04Z","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/2508.07608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speech recognition (AVSR) combines audio-visual modalities to improve speech recognition, especially in noisy environments. However, most existing methods deploy the unidirectional enhancement or symmetric fusion manner, which limits their capability to capture heterogeneous and complementary correlations of audio-visual data-especially under asymmetric information conditions. To tackle these gaps, we introduce a new AVSR framework termed AD-AVSR based on bidirectional modality enhancement. Specifically, we first introduce the audio dual-stream encoding strategy to enrich audio re","authors_text":"Danlei Huang, Fei Yu, Junxiao Xue, Xiaozhen Liu, Xinyi Yin, Xuecheng Wu","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-11T04:23:08Z","title":"AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07608","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":"sha256:21dacfeb6e4520e1e9b8b90bad99008e48eb7ff450dd662e85bc5567333f3019","target":"record","created_at":"2026-07-05T11:52:04Z","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":"9b7e22d9210cae687f8478966465220982d7d30aa87179a5b203786a3f62389a","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-11T04:23:08Z","title_canon_sha256":"eff07e600a1ce5d603e16cabcfe1a9a7aafed942bc63cd26ffa6f8e5152aee15"},"schema_version":"1.0","source":{"id":"2508.07608","kind":"arxiv","version":1}},"canonical_sha256":"6587907ab93b6d9a87845a41c01802edfbe84042eb0c6b0699a4320ede248402","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6587907ab93b6d9a87845a41c01802edfbe84042eb0c6b0699a4320ede248402","first_computed_at":"2026-07-05T11:52:04.702238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:04.702238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0A+BtghqyDMfkJlPCF6n4fiFlgqhabcS1Ba1pKpdUc3uoBBr4vdHyEz71BuW+PcqlYRLM8BML/SEKx3QyK3dAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:04.702764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21dacfeb6e4520e1e9b8b90bad99008e48eb7ff450dd662e85bc5567333f3019","sha256:4dfa87eb4dbc85d0eff93e5d90dfe769ad76f41e880f141b59cf56c1b2f5e0bf"],"state_sha256":"6355155c759c3fa829c07277e4b649c6d10ab89d277b5278719d3d1249c35553"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dwjj6fPyYgU21NniBJpJotpShqZinx5zbNPL/qnINkbz7R69K12nrELk7YCG69GDL/0lvzPVvGE1dONTChKOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:22:55.990089Z","bundle_sha256":"3685e8f61ce57d6e260e230b587c9e3badbaef4c0a51d37c8598b99fb310d9da"}}