{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YNBCF7GUZMG5PP5YRJTBFWJBIZ","short_pith_number":"pith:YNBCF7GU","canonical_record":{"source":{"id":"1810.00108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T22:41:59Z","cross_cats_sorted":[],"title_canon_sha256":"5efccf4a534ec456ad156a312b867492980dd79066c9bc3f65605cc489ad281e","abstract_canon_sha256":"4d1dc132686c0a62d175e61ac760bab25340c2f4819b7b3cbfd5a84a53840948"},"schema_version":"1.0"},"canonical_sha256":"c34222fcd4cb0dd7bfb88a6612d9214674c797405e772f257f58b3cfa94efe8f","source":{"kind":"arxiv","id":"1810.00108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00108","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00108v1","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00108","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"YNBCF7GUZMG5","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YNBCF7GUZMG5PP5Y","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YNBCF7GU","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YNBCF7GUZMG5PP5YRJTBFWJBIZ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T22:41:59Z","cross_cats_sorted":[],"title_canon_sha256":"5efccf4a534ec456ad156a312b867492980dd79066c9bc3f65605cc489ad281e","abstract_canon_sha256":"4d1dc132686c0a62d175e61ac760bab25340c2f4819b7b3cbfd5a84a53840948"},"schema_version":"1.0"},"canonical_sha256":"c34222fcd4cb0dd7bfb88a6612d9214674c797405e772f257f58b3cfa94efe8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:28.749620Z","signature_b64":"gTnqN8nSsmNHTuyza5U7gCyjlv5b1Gk6WenF2dMqHSjzvhwKyFMS29x5HADnu723gUnfQHJpvkVATg3pmVv6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34222fcd4cb0dd7bfb88a6612d9214674c797405e772f257f58b3cfa94efe8f","last_reissued_at":"2026-05-18T00:04:28.749128Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:28.749128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00108","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":"2026-05-18T00:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VGHpN5w5zkvOUrAzI3nlx26+LqV99/kwjsP2fH3ig3oe8B8jJJn8F/nZAkQjj2eyl95LMHwfsYkSTV2Ci+CBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:32:14.799139Z"},"content_sha256":"7b4a4ea5a368873ccc333c5a9d03a61161b2908d35ccd782f4c0064fafc32f5f","schema_version":"1.0","event_id":"sha256:7b4a4ea5a368873ccc333c5a9d03a61161b2908d35ccd782f4c0064fafc32f5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YNBCF7GUZMG5PP5YRJTBFWJBIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Georgios Tzimiropoulos, Maja Pantic, Pingchuan Ma, Stavros Petridis, Themos Stafylakis","submitted_at":"2018-09-28T22:41:59Z","abstract_excerpt":"Recent works in speech recognition rely either on connectionist temporal classification (CTC) or sequence-to-sequence models for character-level recognition. CTC assumes conditional independence of individual characters, whereas attention-based models can provide nonsequential alignments. Therefore, we could use a CTC loss in combination with an attention-based model in order to force monotonic alignments and at the same time get rid of the conditional independence assumption. In this paper, we use the recently proposed hybrid CTC/attention architecture for audio-visual recognition of speech i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00108","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":"2026-05-18T00:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29dORnlMsZln7sGywoB55FE0VREl6hdk74i2W3nIvrd3koN3qN2bSFlNER4Cfif9vX+kns6SGQeEw7GKeyAKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:32:14.799613Z"},"content_sha256":"16885c70d2c590000f09b3ad89ca97c3025d47ded9b583717e7b97d8be568258","schema_version":"1.0","event_id":"sha256:16885c70d2c590000f09b3ad89ca97c3025d47ded9b583717e7b97d8be568258"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ/bundle.json","state_url":"https://pith.science/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ/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":"2026-05-28T22:32:14Z","links":{"resolver":"https://pith.science/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ","bundle":"https://pith.science/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ/bundle.json","state":"https://pith.science/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNBCF7GUZMG5PP5YRJTBFWJBIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YNBCF7GUZMG5PP5YRJTBFWJBIZ","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":"4d1dc132686c0a62d175e61ac760bab25340c2f4819b7b3cbfd5a84a53840948","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T22:41:59Z","title_canon_sha256":"5efccf4a534ec456ad156a312b867492980dd79066c9bc3f65605cc489ad281e"},"schema_version":"1.0","source":{"id":"1810.00108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00108","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00108v1","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00108","created_at":"2026-05-18T00:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"YNBCF7GUZMG5","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YNBCF7GUZMG5PP5Y","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YNBCF7GU","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:16885c70d2c590000f09b3ad89ca97c3025d47ded9b583717e7b97d8be568258","target":"graph","created_at":"2026-05-18T00:04:28Z","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"},"paper":{"abstract_excerpt":"Recent works in speech recognition rely either on connectionist temporal classification (CTC) or sequence-to-sequence models for character-level recognition. CTC assumes conditional independence of individual characters, whereas attention-based models can provide nonsequential alignments. Therefore, we could use a CTC loss in combination with an attention-based model in order to force monotonic alignments and at the same time get rid of the conditional independence assumption. In this paper, we use the recently proposed hybrid CTC/attention architecture for audio-visual recognition of speech i","authors_text":"Georgios Tzimiropoulos, Maja Pantic, Pingchuan Ma, Stavros Petridis, Themos Stafylakis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T22:41:59Z","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00108","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":"sha256:7b4a4ea5a368873ccc333c5a9d03a61161b2908d35ccd782f4c0064fafc32f5f","target":"record","created_at":"2026-05-18T00:04:28Z","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":"4d1dc132686c0a62d175e61ac760bab25340c2f4819b7b3cbfd5a84a53840948","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-28T22:41:59Z","title_canon_sha256":"5efccf4a534ec456ad156a312b867492980dd79066c9bc3f65605cc489ad281e"},"schema_version":"1.0","source":{"id":"1810.00108","kind":"arxiv","version":1}},"canonical_sha256":"c34222fcd4cb0dd7bfb88a6612d9214674c797405e772f257f58b3cfa94efe8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c34222fcd4cb0dd7bfb88a6612d9214674c797405e772f257f58b3cfa94efe8f","first_computed_at":"2026-05-18T00:04:28.749128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:28.749128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gTnqN8nSsmNHTuyza5U7gCyjlv5b1Gk6WenF2dMqHSjzvhwKyFMS29x5HADnu723gUnfQHJpvkVATg3pmVv6BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:28.749620Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b4a4ea5a368873ccc333c5a9d03a61161b2908d35ccd782f4c0064fafc32f5f","sha256:16885c70d2c590000f09b3ad89ca97c3025d47ded9b583717e7b97d8be568258"],"state_sha256":"c01884dfde966c2d905c391c6c0e7c9606800704b5af65878b4202b564a19a7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSFni6BqDVywdG/mL2f+3PoIq3G098FHQKRc5og4ZZfZMTj0KRZnAAIB70tj/OW+f6HV8IKLShK19IDcTSG5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:32:14.802673Z","bundle_sha256":"5fc7d50064c68d2b9670e2c8fc834d3dff7f3739b1acd914e19b2dc2af2126c3"}}