{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ULKLFM6OZC6PW2Y5XXAHF4BFHS","short_pith_number":"pith:ULKLFM6O","canonical_record":{"source":{"id":"1811.05250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T12:28:03Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"e37cc680563d85eb4f85cadb90e1d35760396f6ff61e94f23b8accee2c4f95fd","abstract_canon_sha256":"07d7730b3755c2f29110e93f8dbe7b0e981acc0e344cdf27fde6ae5e9686cd81"},"schema_version":"1.0"},"canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","source":{"kind":"arxiv","id":"1811.05250","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05250","created_at":"2026-05-17T23:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05250v2","created_at":"2026-05-17T23:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05250","created_at":"2026-05-17T23:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"ULKLFM6OZC6P","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"ULKLFM6OZC6PW2Y5","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"ULKLFM6O","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ULKLFM6OZC6PW2Y5XXAHF4BFHS","target":"record","payload":{"canonical_record":{"source":{"id":"1811.05250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T12:28:03Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"e37cc680563d85eb4f85cadb90e1d35760396f6ff61e94f23b8accee2c4f95fd","abstract_canon_sha256":"07d7730b3755c2f29110e93f8dbe7b0e981acc0e344cdf27fde6ae5e9686cd81"},"schema_version":"1.0"},"canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:59.145102Z","signature_b64":"9dP9LPEUZB2K3qS0f8p6XCSDVHInzzM/Rj7SZ+jCNIy0diZ0D0lSCdFOdhpjhFFhSEsOhPCkBLljpbdVi9QCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","last_reissued_at":"2026-05-17T23:47:59.144542Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:59.144542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.05250","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":"2026-05-17T23:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/12ULr4APBA/ZEnlA1JclUr/ift2KzWITNycMrIE+ORRosVQonY3GHowKi4p8obMVV+khJob48s+bUInWC27Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:31:34.706846Z"},"content_sha256":"dfb55ff6805da98eeddb2c247c3c8c7cae9d580b1ffc9248bbea28aab8593f20","schema_version":"1.0","event_id":"sha256:dfb55ff6805da98eeddb2c247c3c8c7cae9d580b1ffc9248bbea28aab8593f20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ULKLFM6OZC6PW2Y5XXAHF4BFHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modality Attention for End-to-End 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.CL","authors_text":"Jia Jia, Pan Zhou, Wei Chen, Wenwen Yang, Yanfeng Wang","submitted_at":"2018-11-13T12:28:03Z","abstract_excerpt":"Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05250","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":""},"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":"2026-05-17T23:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tox8aXXD7UY5ipRE559TJT0PkI+togZCjPT40Jw7lE503SZGzY3janvz+rmTaSpZuC9tUOB/pWr4nx7W0cuSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:31:34.707548Z"},"content_sha256":"c747c2c166f4c52b71ae4ca58f54ed81c458f0cb5bde9d44fdc03a91929b2ddb","schema_version":"1.0","event_id":"sha256:c747c2c166f4c52b71ae4ca58f54ed81c458f0cb5bde9d44fdc03a91929b2ddb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/bundle.json","state_url":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/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":"2026-05-27T07:31:34Z","links":{"resolver":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS","bundle":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/bundle.json","state":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ULKLFM6OZC6PW2Y5XXAHF4BFHS","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":"07d7730b3755c2f29110e93f8dbe7b0e981acc0e344cdf27fde6ae5e9686cd81","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T12:28:03Z","title_canon_sha256":"e37cc680563d85eb4f85cadb90e1d35760396f6ff61e94f23b8accee2c4f95fd"},"schema_version":"1.0","source":{"id":"1811.05250","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05250","created_at":"2026-05-17T23:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05250v2","created_at":"2026-05-17T23:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05250","created_at":"2026-05-17T23:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"ULKLFM6OZC6P","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"ULKLFM6OZC6PW2Y5","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"ULKLFM6O","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:c747c2c166f4c52b71ae4ca58f54ed81c458f0cb5bde9d44fdc03a91929b2ddb","target":"graph","created_at":"2026-05-17T23:47:59Z","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"},"paper":{"abstract_excerpt":"Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the di","authors_text":"Jia Jia, Pan Zhou, Wei Chen, Wenwen Yang, Yanfeng Wang","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T12:28:03Z","title":"Modality Attention for End-to-End Audio-visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05250","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:dfb55ff6805da98eeddb2c247c3c8c7cae9d580b1ffc9248bbea28aab8593f20","target":"record","created_at":"2026-05-17T23:47:59Z","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":"07d7730b3755c2f29110e93f8dbe7b0e981acc0e344cdf27fde6ae5e9686cd81","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T12:28:03Z","title_canon_sha256":"e37cc680563d85eb4f85cadb90e1d35760396f6ff61e94f23b8accee2c4f95fd"},"schema_version":"1.0","source":{"id":"1811.05250","kind":"arxiv","version":2}},"canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","first_computed_at":"2026-05-17T23:47:59.144542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:59.144542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9dP9LPEUZB2K3qS0f8p6XCSDVHInzzM/Rj7SZ+jCNIy0diZ0D0lSCdFOdhpjhFFhSEsOhPCkBLljpbdVi9QCCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:59.145102Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05250","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfb55ff6805da98eeddb2c247c3c8c7cae9d580b1ffc9248bbea28aab8593f20","sha256:c747c2c166f4c52b71ae4ca58f54ed81c458f0cb5bde9d44fdc03a91929b2ddb"],"state_sha256":"aef64c16a9c377dc0bc34c31f2ba944bb71b378c1e6fa178910d02ba3fb09e55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSERwFV48eM5PeMDBDMcAjTGrTer4ElUkQx1Qe3J3ouicFT1aUnQ1aK3OXfZegyBVGJnKEvoSezlF4h4DovYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:31:34.711169Z","bundle_sha256":"c3ab7a8f4802ab12482e3f52f3a7d49f8b857068c29987433ccc9d935d9deefb"}}