{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:R2CMXOT2BC42WC3UOQPNLTAGXN","short_pith_number":"pith:R2CMXOT2","canonical_record":{"source":{"id":"2012.07528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-28T12:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"c6892a9651121a346d613fc31a50e12d1c9374a232e2d31254f9b86fab3dfd0f","abstract_canon_sha256":"6b8136dc0efb3fffeec650417b1c43850eee808e6c83bf93c6973d99911c0ccb"},"schema_version":"1.0"},"canonical_sha256":"8e84cbba7a08b9ab0b74741ed5cc06bb6a9749522ea95e1c899b7eaa2dc255e7","source":{"kind":"arxiv","id":"2012.07528","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07528","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07528v1","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07528","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"R2CMXOT2BC42","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"R2CMXOT2BC42WC3U","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"R2CMXOT2","created_at":"2026-07-05T01:59:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:R2CMXOT2BC42WC3UOQPNLTAGXN","target":"record","payload":{"canonical_record":{"source":{"id":"2012.07528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-28T12:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"c6892a9651121a346d613fc31a50e12d1c9374a232e2d31254f9b86fab3dfd0f","abstract_canon_sha256":"6b8136dc0efb3fffeec650417b1c43850eee808e6c83bf93c6973d99911c0ccb"},"schema_version":"1.0"},"canonical_sha256":"8e84cbba7a08b9ab0b74741ed5cc06bb6a9749522ea95e1c899b7eaa2dc255e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:21.462615Z","signature_b64":"3lYr84+Q9Bp49I13t/Hx5zYlXEqfhELM8zJidr+Qow5KJAGjMU84S1kbE6KITb85GEk/53U4ktzoxg712o+mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e84cbba7a08b9ab0b74741ed5cc06bb6a9749522ea95e1c899b7eaa2dc255e7","last_reissued_at":"2026-07-05T01:59:21.462237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:21.462237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.07528","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":"2026-07-05T01:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SK2oXO4j+fDGGG+cf9uktu01wpDRosWXMW+i42Ha9ctx42S8WoHXXzyfVK7kFoyp0AIvg7qX1qhGYq4LS1+WBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:59:44.837139Z"},"content_sha256":"38a8bd0d176ee33641a7d7a5e39e3cb49aa3f6a0d9acca0a4689c197ca3e037f","schema_version":"1.0","event_id":"sha256:38a8bd0d176ee33641a7d7a5e39e3cb49aa3f6a0d9acca0a4689c197ca3e037f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:R2CMXOT2BC42WC3UOQPNLTAGXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling Homophemes in Lip Reading using Perplexity Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daqing Chen, Kun Guo, Perry Xiao, Souheil Fenghour","submitted_at":"2020-11-28T12:12:17Z","abstract_excerpt":"The performance of automated lip reading using visemes as a classification schema has achieved less success compared with the use of ASCII characters and words largely due to the problem of different words sharing identical visemes. The Generative Pre-Training transformer is an effective autoregressive language model used for many tasks in Natural Language Processing, including sentence prediction and text classification.\n  This paper proposes a new application for this model and applies it in the context of lip reading, where it serves as a language model to convert visual speech in the form "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07528","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.07528/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":"2026-07-05T01:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UvGCRv5sM8FkYuzklIeTJ5hALvo+BsORasm8qmq2tzWwBM+nzBVLlqrzXm2XaG/rWuDEqc6UqLvZjnwAKN3TDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:59:44.837527Z"},"content_sha256":"0a3eb213ec635919a5ed5f60d35a884de20bc08617806dc324585e236979126e","schema_version":"1.0","event_id":"sha256:0a3eb213ec635919a5ed5f60d35a884de20bc08617806dc324585e236979126e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2CMXOT2BC42WC3UOQPNLTAGXN/bundle.json","state_url":"https://pith.science/pith/R2CMXOT2BC42WC3UOQPNLTAGXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2CMXOT2BC42WC3UOQPNLTAGXN/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":"2026-08-17T04:59:44Z","links":{"resolver":"https://pith.science/pith/R2CMXOT2BC42WC3UOQPNLTAGXN","bundle":"https://pith.science/pith/R2CMXOT2BC42WC3UOQPNLTAGXN/bundle.json","state":"https://pith.science/pith/R2CMXOT2BC42WC3UOQPNLTAGXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2CMXOT2BC42WC3UOQPNLTAGXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R2CMXOT2BC42WC3UOQPNLTAGXN","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":"6b8136dc0efb3fffeec650417b1c43850eee808e6c83bf93c6973d99911c0ccb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-28T12:12:17Z","title_canon_sha256":"c6892a9651121a346d613fc31a50e12d1c9374a232e2d31254f9b86fab3dfd0f"},"schema_version":"1.0","source":{"id":"2012.07528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07528","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07528v1","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07528","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"R2CMXOT2BC42","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"R2CMXOT2BC42WC3U","created_at":"2026-07-05T01:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"R2CMXOT2","created_at":"2026-07-05T01:59:21Z"}],"graph_snapshots":[{"event_id":"sha256:0a3eb213ec635919a5ed5f60d35a884de20bc08617806dc324585e236979126e","target":"graph","created_at":"2026-07-05T01:59:21Z","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/2012.07528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of automated lip reading using visemes as a classification schema has achieved less success compared with the use of ASCII characters and words largely due to the problem of different words sharing identical visemes. The Generative Pre-Training transformer is an effective autoregressive language model used for many tasks in Natural Language Processing, including sentence prediction and text classification.\n  This paper proposes a new application for this model and applies it in the context of lip reading, where it serves as a language model to convert visual speech in the form ","authors_text":"Daqing Chen, Kun Guo, Perry Xiao, Souheil Fenghour","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-28T12:12:17Z","title":"Disentangling Homophemes in Lip Reading using Perplexity Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07528","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":"sha256:38a8bd0d176ee33641a7d7a5e39e3cb49aa3f6a0d9acca0a4689c197ca3e037f","target":"record","created_at":"2026-07-05T01:59:21Z","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":"6b8136dc0efb3fffeec650417b1c43850eee808e6c83bf93c6973d99911c0ccb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-28T12:12:17Z","title_canon_sha256":"c6892a9651121a346d613fc31a50e12d1c9374a232e2d31254f9b86fab3dfd0f"},"schema_version":"1.0","source":{"id":"2012.07528","kind":"arxiv","version":1}},"canonical_sha256":"8e84cbba7a08b9ab0b74741ed5cc06bb6a9749522ea95e1c899b7eaa2dc255e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e84cbba7a08b9ab0b74741ed5cc06bb6a9749522ea95e1c899b7eaa2dc255e7","first_computed_at":"2026-07-05T01:59:21.462237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:21.462237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3lYr84+Q9Bp49I13t/Hx5zYlXEqfhELM8zJidr+Qow5KJAGjMU84S1kbE6KITb85GEk/53U4ktzoxg712o+mDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:21.462615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.07528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38a8bd0d176ee33641a7d7a5e39e3cb49aa3f6a0d9acca0a4689c197ca3e037f","sha256:0a3eb213ec635919a5ed5f60d35a884de20bc08617806dc324585e236979126e"],"state_sha256":"329b5172f0d082011dffd1020c44184d9df827e7860f2da035aa2fb80fa2a97b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yTA+jtzvoO5XGdQyDvOwxO1V6CkoGOXibkmowxeMwiT/JfMZ+zjTav0DZ9g4BLBuWPUpCGweZiUtPO/MIXfvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:59:44.839974Z","bundle_sha256":"9a8c5fa9c95b37ef6ae8661cf75de31b04e1932060086314bd344f16d3622979"}}