{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XJQFS3MORGHBSBQ2GCP6U5DMQA","short_pith_number":"pith:XJQFS3MO","canonical_record":{"source":{"id":"2211.02133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T20:20:47Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"6ae4aab2431c458cae813af67aff51a7418284849be902e236ff9589afc4d19b","abstract_canon_sha256":"0fdf7bbbc993677b26be57333a30a0f446e03e44eb4cc760b64e1116dea20de4"},"schema_version":"1.0"},"canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","source":{"kind":"arxiv","id":"2211.02133","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02133","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02133v2","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02133","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"XJQFS3MORGHB","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"XJQFS3MORGHBSBQ2","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"XJQFS3MO","created_at":"2026-07-05T06:26:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XJQFS3MORGHBSBQ2GCP6U5DMQA","target":"record","payload":{"canonical_record":{"source":{"id":"2211.02133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T20:20:47Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"6ae4aab2431c458cae813af67aff51a7418284849be902e236ff9589afc4d19b","abstract_canon_sha256":"0fdf7bbbc993677b26be57333a30a0f446e03e44eb4cc760b64e1116dea20de4"},"schema_version":"1.0"},"canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:43.903935Z","signature_b64":"fsm/bAu7a1qGozyGyCVIRra1QaPbLLzQ/ZVq1YfoBl9CZ7zOHMuX9kPzx1Ip0oCoCZJBH2+HK8EDj16WKnEjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","last_reissued_at":"2026-07-05T06:26:43.903455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:43.903455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.02133","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":"2026-07-05T06:26:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"trtSHlDNAaLnwlu2vwY9C4c/dKRhjZ2UGSKybzudcgnmDn1QDWBhXwrjgsOaIl/O1O8DVxtfc41u/4OQweXrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:01:09.377091Z"},"content_sha256":"c458816aa9b869bb7e8cb2ae398396c4749618f554e12ec38d25cfcd9f8dddf6","schema_version":"1.0","event_id":"sha256:c458816aa9b869bb7e8cb2ae398396c4749618f554e12ec38d25cfcd9f8dddf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XJQFS3MORGHBSBQ2GCP6U5DMQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Maja Pantic, Niko Moritz, Pingchuan Ma, Stavros Petridis","submitted_at":"2022-11-03T20:20:47Z","abstract_excerpt":"In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. Additionally, we propose a novel alignment regularization technique that promotes s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02133","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/2211.02133/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":"2026-07-05T06:26:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rrRqT59c+go9DjQhLSnQbemfnvK5ElbnQtyLeF9bz3BxTMxT/GgDdY+3prL02fJkh6xI3t3FVddv8SKKtzbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:01:09.377481Z"},"content_sha256":"5ed227fe9664dae028660a060d974aa3f2b1a6d1937ec59458dd2eef85eedb24","schema_version":"1.0","event_id":"sha256:5ed227fe9664dae028660a060d974aa3f2b1a6d1937ec59458dd2eef85eedb24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/bundle.json","state_url":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/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":"2026-07-09T06:01:09Z","links":{"resolver":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA","bundle":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/bundle.json","state":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XJQFS3MORGHBSBQ2GCP6U5DMQA","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":"0fdf7bbbc993677b26be57333a30a0f446e03e44eb4cc760b64e1116dea20de4","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T20:20:47Z","title_canon_sha256":"6ae4aab2431c458cae813af67aff51a7418284849be902e236ff9589afc4d19b"},"schema_version":"1.0","source":{"id":"2211.02133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02133","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02133v2","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02133","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"XJQFS3MORGHB","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"XJQFS3MORGHBSBQ2","created_at":"2026-07-05T06:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"XJQFS3MO","created_at":"2026-07-05T06:26:43Z"}],"graph_snapshots":[{"event_id":"sha256:5ed227fe9664dae028660a060d974aa3f2b1a6d1937ec59458dd2eef85eedb24","target":"graph","created_at":"2026-07-05T06:26:43Z","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/2211.02133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. Additionally, we propose a novel alignment regularization technique that promotes s","authors_text":"Christian Fuegen, Maja Pantic, Niko Moritz, Pingchuan Ma, Stavros Petridis","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T20:20:47Z","title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02133","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:c458816aa9b869bb7e8cb2ae398396c4749618f554e12ec38d25cfcd9f8dddf6","target":"record","created_at":"2026-07-05T06:26:43Z","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":"0fdf7bbbc993677b26be57333a30a0f446e03e44eb4cc760b64e1116dea20de4","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T20:20:47Z","title_canon_sha256":"6ae4aab2431c458cae813af67aff51a7418284849be902e236ff9589afc4d19b"},"schema_version":"1.0","source":{"id":"2211.02133","kind":"arxiv","version":2}},"canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","first_computed_at":"2026-07-05T06:26:43.903455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:43.903455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fsm/bAu7a1qGozyGyCVIRra1QaPbLLzQ/ZVq1YfoBl9CZ7zOHMuX9kPzx1Ip0oCoCZJBH2+HK8EDj16WKnEjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:43.903935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c458816aa9b869bb7e8cb2ae398396c4749618f554e12ec38d25cfcd9f8dddf6","sha256:5ed227fe9664dae028660a060d974aa3f2b1a6d1937ec59458dd2eef85eedb24"],"state_sha256":"b1087b1b954a7212987e0b0cc4d5b6ddcd34c22c33018c15add85df04ac5c113"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ylr+ade4ULONqsMnOjkiExOqoLL8FPCbaMaOeBbXvXCYMNnWNaZqw8WQDS1lvsrPMJFH/nMvItfyp9uYFDwxBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:01:09.379647Z","bundle_sha256":"20b3995ac6d34f80062c5eb37bb9f5105bb02da7820523752063266d11b1c4db"}}