{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AO3WHZTA47Q3Q7J3U4MA3R3ERN","short_pith_number":"pith:AO3WHZTA","canonical_record":{"source":{"id":"1903.09616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-22T17:24:37Z","cross_cats_sorted":[],"title_canon_sha256":"d0ca56eeb10ee6f01345249400a213d0c1c403c740cf5d909c07d8634e7516ce","abstract_canon_sha256":"23074a75d0bc3e87bd233c2b2819f909c3ca6dacf902ffcb14ea15843280b14f"},"schema_version":"1.0"},"canonical_sha256":"03b763e660e7e1b87d3ba7180dc7648b4ac5a2a0846e8fa7d45d48364086a76d","source":{"kind":"arxiv","id":"1903.09616","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09616","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09616v2","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09616","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"AO3WHZTA47Q3","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"AO3WHZTA47Q3Q7J3","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"AO3WHZTA","created_at":"2026-07-05T00:04:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AO3WHZTA47Q3Q7J3U4MA3R3ERN","target":"record","payload":{"canonical_record":{"source":{"id":"1903.09616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-22T17:24:37Z","cross_cats_sorted":[],"title_canon_sha256":"d0ca56eeb10ee6f01345249400a213d0c1c403c740cf5d909c07d8634e7516ce","abstract_canon_sha256":"23074a75d0bc3e87bd233c2b2819f909c3ca6dacf902ffcb14ea15843280b14f"},"schema_version":"1.0"},"canonical_sha256":"03b763e660e7e1b87d3ba7180dc7648b4ac5a2a0846e8fa7d45d48364086a76d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:40.824672Z","signature_b64":"juCT17UGFt67UICOMPn8tvQC1mqgK3TaifRnoGtXgxttJHw4GcxqegpOxxhhvgG8mWx0jF/5Xkxhu2ggIoDVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b763e660e7e1b87d3ba7180dc7648b4ac5a2a0846e8fa7d45d48364086a76d","last_reissued_at":"2026-07-05T00:04:40.824295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:40.824295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.09616","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":"2026-07-05T00:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5mm5pnWHqYH0Bfwd6G9UwIkCxyfVJafhdeiuKMMcba2lSPnUpflIjB+5rlBEhHlUiHKAGY23U6yjv2NJAFGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:13:40.707679Z"},"content_sha256":"3e4603ee12733a9a2cc415c6090870162048eccbdc7e25864d665909f94f50cc","schema_version":"1.0","event_id":"sha256:3e4603ee12733a9a2cc415c6090870162048eccbdc7e25864d665909f94f50cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AO3WHZTA47Q3Q7J3U4MA3R3ERN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Importance of Video Action Recognition for Visual Lipreading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinshuo Weng","submitted_at":"2019-03-22T17:24:37Z","abstract_excerpt":"We focus on the word-level visual lipreading, which requires to decode the word from the speaker's video. Recently, many state-of-the-art visual lipreading methods explore the end-to-end trainable deep models, involving the use of 2D convolutional networks (e.g., ResNet) as the front-end visual feature extractor and the sequential model (e.g., Bi-LSTM or Bi-GRU) as the back-end. Although a deep 2D convolution neural network can provide informative image-based features, it ignores the temporal motion existing between the adjacent frames. In this work, we investigate the spatial-temporal capacit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09616","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/1903.09616/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":"2026-07-05T00:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+C1D4aKNKaL2jlO03fLyneT/B8qAinL3jZArVJ8X4XuAdixVZHsfNtdUTT9LWjd5QhgOpWwnUtw8M/HJKcPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:13:40.708197Z"},"content_sha256":"81020dd5c0ad5390cb79c3dd3cebdf9e761b59aaa7d4a6a19e01a6e0b44fbee5","schema_version":"1.0","event_id":"sha256:81020dd5c0ad5390cb79c3dd3cebdf9e761b59aaa7d4a6a19e01a6e0b44fbee5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN/bundle.json","state_url":"https://pith.science/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN/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":"2026-07-31T14:13:40Z","links":{"resolver":"https://pith.science/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN","bundle":"https://pith.science/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN/bundle.json","state":"https://pith.science/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AO3WHZTA47Q3Q7J3U4MA3R3ERN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AO3WHZTA47Q3Q7J3U4MA3R3ERN","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":"23074a75d0bc3e87bd233c2b2819f909c3ca6dacf902ffcb14ea15843280b14f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-22T17:24:37Z","title_canon_sha256":"d0ca56eeb10ee6f01345249400a213d0c1c403c740cf5d909c07d8634e7516ce"},"schema_version":"1.0","source":{"id":"1903.09616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09616","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09616v2","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09616","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"AO3WHZTA47Q3","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"AO3WHZTA47Q3Q7J3","created_at":"2026-07-05T00:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"AO3WHZTA","created_at":"2026-07-05T00:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:81020dd5c0ad5390cb79c3dd3cebdf9e761b59aaa7d4a6a19e01a6e0b44fbee5","target":"graph","created_at":"2026-07-05T00:04:40Z","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/1903.09616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on the word-level visual lipreading, which requires to decode the word from the speaker's video. Recently, many state-of-the-art visual lipreading methods explore the end-to-end trainable deep models, involving the use of 2D convolutional networks (e.g., ResNet) as the front-end visual feature extractor and the sequential model (e.g., Bi-LSTM or Bi-GRU) as the back-end. Although a deep 2D convolution neural network can provide informative image-based features, it ignores the temporal motion existing between the adjacent frames. In this work, we investigate the spatial-temporal capacit","authors_text":"Xinshuo Weng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-22T17:24:37Z","title":"On the Importance of Video Action Recognition for Visual Lipreading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09616","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":"sha256:3e4603ee12733a9a2cc415c6090870162048eccbdc7e25864d665909f94f50cc","target":"record","created_at":"2026-07-05T00:04:40Z","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":"23074a75d0bc3e87bd233c2b2819f909c3ca6dacf902ffcb14ea15843280b14f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-22T17:24:37Z","title_canon_sha256":"d0ca56eeb10ee6f01345249400a213d0c1c403c740cf5d909c07d8634e7516ce"},"schema_version":"1.0","source":{"id":"1903.09616","kind":"arxiv","version":2}},"canonical_sha256":"03b763e660e7e1b87d3ba7180dc7648b4ac5a2a0846e8fa7d45d48364086a76d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03b763e660e7e1b87d3ba7180dc7648b4ac5a2a0846e8fa7d45d48364086a76d","first_computed_at":"2026-07-05T00:04:40.824295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:40.824295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"juCT17UGFt67UICOMPn8tvQC1mqgK3TaifRnoGtXgxttJHw4GcxqegpOxxhhvgG8mWx0jF/5Xkxhu2ggIoDVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:40.824672Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.09616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e4603ee12733a9a2cc415c6090870162048eccbdc7e25864d665909f94f50cc","sha256:81020dd5c0ad5390cb79c3dd3cebdf9e761b59aaa7d4a6a19e01a6e0b44fbee5"],"state_sha256":"05bab4b09d3893e4af805d57c41bed352bd7f332283d1bfe15985c52add34282"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQNDEvUDSORXUJgFpFoyt/jbaylK/r3cCEX0MnCxj1zu3tqAkn8+lKXwJWS5Yk6IcN1sJ5g1v63gwG4vh1ljDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:13:40.714024Z","bundle_sha256":"36912b77482274b68cb8ca3640154a73b81536d53e55938b6eeeb3dc540bff45"}}