{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JEYOUZTQ7BJ5JPV4IVTNZP2BTU","short_pith_number":"pith:JEYOUZTQ","canonical_record":{"source":{"id":"1905.02540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-04T02:32:06Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"ff43d87235329b15413aa1723a7889ebb2a28c9b6cdce8b2ae53a68964000172","abstract_canon_sha256":"ab1ecccc4b7dc06e999f6a9ea7dc0c799fa649c8d3c6dc296bb26389de21af2c"},"schema_version":"1.0"},"canonical_sha256":"4930ea6670f853d4bebc4566dcbf419d3802de84ee66452cd561d4198f8f9f8c","source":{"kind":"arxiv","id":"1905.02540","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02540","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02540v2","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02540","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"JEYOUZTQ7BJ5","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"JEYOUZTQ7BJ5JPV4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"JEYOUZTQ","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JEYOUZTQ7BJ5JPV4IVTNZP2BTU","target":"record","payload":{"canonical_record":{"source":{"id":"1905.02540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-04T02:32:06Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"ff43d87235329b15413aa1723a7889ebb2a28c9b6cdce8b2ae53a68964000172","abstract_canon_sha256":"ab1ecccc4b7dc06e999f6a9ea7dc0c799fa649c8d3c6dc296bb26389de21af2c"},"schema_version":"1.0"},"canonical_sha256":"4930ea6670f853d4bebc4566dcbf419d3802de84ee66452cd561d4198f8f9f8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:10.819667Z","signature_b64":"wGPue+pApJUmf51NktPplSqaqIIsqEydsMiiEvvke9NwkDNDFhvtUXc4e/iD144ydxnp/a0CVzDQNXfxg+sMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4930ea6670f853d4bebc4566dcbf419d3802de84ee66452cd561d4198f8f9f8c","last_reissued_at":"2026-05-17T23:40:10.818973Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:10.818973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.02540","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":"2026-05-17T23:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F5WdaUDM1sAbOCEMlzph4kIIv2KEtS10N1Mo1A7oCcFiIgo7wcCCkOsKFT/732ZEm1LBjgz2D3tj64DsuYcZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:47:53.069278Z"},"content_sha256":"c51b69c8a9ece98f68c6861eea6a397b807d087553c8072552bb2d4719d3a712","schema_version":"1.0","event_id":"sha256:c51b69c8a9ece98f68c6861eea6a397b807d087553c8072552bb2d4719d3a712"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JEYOUZTQ7BJ5JPV4IVTNZP2BTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Kris Kitani, Xinshuo Weng","submitted_at":"2019-05-04T02:32:06Z","abstract_excerpt":"We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. State-of-the-art methods explore the use of end-to-end neural networks, including a shallow (up to three layers) 3D convolutional neural network (CNN) + a deep 2D CNN (e.g., ResNet) as the front-end to extract visual features, and a recurrent neural network (e.g., bidirectional LSTM) as the back-end for classification. In this work, we propose to replace the shallow 3D CNNs + deep 2D CNNs front-end with recent successful deep 3D CNNs --- two-stream (i.e., gray"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02540","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":"2026-05-17T23:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T5iBOn6sDzqiku9VptL0Bpgb/gvbNVF66zZSrN0ezhwecGsFK9GfRun4HVR6u91DaOw94UOcB7le2f5gdeKvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:47:53.069649Z"},"content_sha256":"4999978f5ed1b41169db9cb2a68f4d7b54413e127d8c8dfce85018a797a16212","schema_version":"1.0","event_id":"sha256:4999978f5ed1b41169db9cb2a68f4d7b54413e127d8c8dfce85018a797a16212"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU/bundle.json","state_url":"https://pith.science/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU/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":"2026-06-04T04:47:53Z","links":{"resolver":"https://pith.science/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU","bundle":"https://pith.science/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU/bundle.json","state":"https://pith.science/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEYOUZTQ7BJ5JPV4IVTNZP2BTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JEYOUZTQ7BJ5JPV4IVTNZP2BTU","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":"ab1ecccc4b7dc06e999f6a9ea7dc0c799fa649c8d3c6dc296bb26389de21af2c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-04T02:32:06Z","title_canon_sha256":"ff43d87235329b15413aa1723a7889ebb2a28c9b6cdce8b2ae53a68964000172"},"schema_version":"1.0","source":{"id":"1905.02540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02540","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02540v2","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02540","created_at":"2026-05-17T23:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"JEYOUZTQ7BJ5","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"JEYOUZTQ7BJ5JPV4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"JEYOUZTQ","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:4999978f5ed1b41169db9cb2a68f4d7b54413e127d8c8dfce85018a797a16212","target":"graph","created_at":"2026-05-17T23:40:10Z","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":"We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. State-of-the-art methods explore the use of end-to-end neural networks, including a shallow (up to three layers) 3D convolutional neural network (CNN) + a deep 2D CNN (e.g., ResNet) as the front-end to extract visual features, and a recurrent neural network (e.g., bidirectional LSTM) as the back-end for classification. In this work, we propose to replace the shallow 3D CNNs + deep 2D CNNs front-end with recent successful deep 3D CNNs --- two-stream (i.e., gray","authors_text":"Kris Kitani, Xinshuo Weng","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-04T02:32:06Z","title":"Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02540","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:c51b69c8a9ece98f68c6861eea6a397b807d087553c8072552bb2d4719d3a712","target":"record","created_at":"2026-05-17T23:40:10Z","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":"ab1ecccc4b7dc06e999f6a9ea7dc0c799fa649c8d3c6dc296bb26389de21af2c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-04T02:32:06Z","title_canon_sha256":"ff43d87235329b15413aa1723a7889ebb2a28c9b6cdce8b2ae53a68964000172"},"schema_version":"1.0","source":{"id":"1905.02540","kind":"arxiv","version":2}},"canonical_sha256":"4930ea6670f853d4bebc4566dcbf419d3802de84ee66452cd561d4198f8f9f8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4930ea6670f853d4bebc4566dcbf419d3802de84ee66452cd561d4198f8f9f8c","first_computed_at":"2026-05-17T23:40:10.818973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:10.818973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wGPue+pApJUmf51NktPplSqaqIIsqEydsMiiEvvke9NwkDNDFhvtUXc4e/iD144ydxnp/a0CVzDQNXfxg+sMCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:10.819667Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.02540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c51b69c8a9ece98f68c6861eea6a397b807d087553c8072552bb2d4719d3a712","sha256:4999978f5ed1b41169db9cb2a68f4d7b54413e127d8c8dfce85018a797a16212"],"state_sha256":"4c5b6c540f6b8ea24888ec2e9abef9d88f6aa20e7dd6b43469863a1d1c91e5a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Z1l7f3J+9Au0v7RXnHytmQzBOqc9qtR8mTjlnO23fMZdY4mk+fADwQx4GpQXonD3j7eex4A/I75Ua4Ogv3ZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T04:47:53.072785Z","bundle_sha256":"358d7c7bd92d3be4de05f5afbfced095606cf945e97dd0c798743ff617234015"}}