{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LX676QJWKUBJSZ2KVWZLBOA6MW","short_pith_number":"pith:LX676QJW","canonical_record":{"source":{"id":"1804.11127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T11:27:26Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"ea35fb20027946b5d81c758e43d8070705b93c9df95d0c4206b791cfa84eb2c3","abstract_canon_sha256":"61a1c8d9116fb3b2af0a45c129a8ee41e8da19b02ae5f5c2973322a608209679"},"schema_version":"1.0"},"canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","source":{"kind":"arxiv","id":"1804.11127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11127","created_at":"2026-05-18T00:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11127v1","created_at":"2026-05-18T00:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11127","created_at":"2026-05-18T00:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"LX676QJWKUBJ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LX676QJWKUBJSZ2K","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LX676QJW","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LX676QJWKUBJSZ2KVWZLBOA6MW","target":"record","payload":{"canonical_record":{"source":{"id":"1804.11127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T11:27:26Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"ea35fb20027946b5d81c758e43d8070705b93c9df95d0c4206b791cfa84eb2c3","abstract_canon_sha256":"61a1c8d9116fb3b2af0a45c129a8ee41e8da19b02ae5f5c2973322a608209679"},"schema_version":"1.0"},"canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:14.560717Z","signature_b64":"Th6mWXd3FqnlZGT0yeyUeWrSEEUVZ5qGIue30FJddA4cFVFeHz63WYZpXSxIWf0XVuIxdyUFbErkd5oGCSn2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","last_reissued_at":"2026-05-18T00:17:14.560006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:14.560006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.11127","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":"2026-05-18T00:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qujk3rfwmmDq2nmTm7doysMXcWdXclgsqtgmoD5BgNh0Sy5KVgAb2UGl7lVeApoEmiMRsGY52YzL+oRM/UxnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T20:06:39.481811Z"},"content_sha256":"a30b190c91b7d2db2a173cc0978ded53f2ee4703780a92d71c9ac2234dfb078f","schema_version":"1.0","event_id":"sha256:a30b190c91b7d2db2a173cc0978ded53f2ee4703780a92d71c9ac2234dfb078f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LX676QJWKUBJSZ2KVWZLBOA6MW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigations on End-to-End Audiovisual Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Juergen Schmidhuber, Michael Wand, Ngoc Thang Vu","submitted_at":"2018-04-30T11:27:26Z","abstract_excerpt":"Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separately model the process of decision fusion as in conventional (e.g. HMM-based) systems. The fusion system outperforms single-modality recognition under all noise conditions. Investigation of the saliency of the input features shows that the neural network automatically adapts to different noise levels i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11127","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":""},"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":"2026-05-18T00:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YY/PTNA1UdNcU9I89ViZQ5Srd/OAqqk/m0pWNVgawQPqOMtDAGBn74e2iixkiVVG48khW7aeIU0K+/2WIYMEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T20:06:39.482342Z"},"content_sha256":"458d191f5789849b849f410ee7e2388a1dee2e8f8030375cf8504a5d9a594bce","schema_version":"1.0","event_id":"sha256:458d191f5789849b849f410ee7e2388a1dee2e8f8030375cf8504a5d9a594bce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/bundle.json","state_url":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/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":"2026-05-20T20:06:39Z","links":{"resolver":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW","bundle":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/bundle.json","state":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LX676QJWKUBJSZ2KVWZLBOA6MW","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":"61a1c8d9116fb3b2af0a45c129a8ee41e8da19b02ae5f5c2973322a608209679","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T11:27:26Z","title_canon_sha256":"ea35fb20027946b5d81c758e43d8070705b93c9df95d0c4206b791cfa84eb2c3"},"schema_version":"1.0","source":{"id":"1804.11127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11127","created_at":"2026-05-18T00:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11127v1","created_at":"2026-05-18T00:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11127","created_at":"2026-05-18T00:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"LX676QJWKUBJ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LX676QJWKUBJSZ2K","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LX676QJW","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:458d191f5789849b849f410ee7e2388a1dee2e8f8030375cf8504a5d9a594bce","target":"graph","created_at":"2026-05-18T00:17:14Z","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":"Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separately model the process of decision fusion as in conventional (e.g. HMM-based) systems. The fusion system outperforms single-modality recognition under all noise conditions. Investigation of the saliency of the input features shows that the neural network automatically adapts to different noise levels i","authors_text":"Juergen Schmidhuber, Michael Wand, Ngoc Thang Vu","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T11:27:26Z","title":"Investigations on End-to-End Audiovisual Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11127","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:a30b190c91b7d2db2a173cc0978ded53f2ee4703780a92d71c9ac2234dfb078f","target":"record","created_at":"2026-05-18T00:17:14Z","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":"61a1c8d9116fb3b2af0a45c129a8ee41e8da19b02ae5f5c2973322a608209679","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T11:27:26Z","title_canon_sha256":"ea35fb20027946b5d81c758e43d8070705b93c9df95d0c4206b791cfa84eb2c3"},"schema_version":"1.0","source":{"id":"1804.11127","kind":"arxiv","version":1}},"canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","first_computed_at":"2026-05-18T00:17:14.560006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:14.560006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Th6mWXd3FqnlZGT0yeyUeWrSEEUVZ5qGIue30FJddA4cFVFeHz63WYZpXSxIWf0XVuIxdyUFbErkd5oGCSn2AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:14.560717Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.11127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a30b190c91b7d2db2a173cc0978ded53f2ee4703780a92d71c9ac2234dfb078f","sha256:458d191f5789849b849f410ee7e2388a1dee2e8f8030375cf8504a5d9a594bce"],"state_sha256":"a8503371847ef9bc94756658c93d1768ad2b6b52d55e931e5f2beceeaa59717d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAGJBtEEEWK5AA9h9JvvE6M4cTP7L1o0JeK/dn+1MXiBQKV3WiTUwk29Mdo8LzGT5HpYyXyAwkZBEFp/IJhzBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T20:06:39.484866Z","bundle_sha256":"d61458009b509498e04fc4655a6e6710336b3ca9cc78dc925a9e6828f15215e6"}}