{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GIMYHKSJZF6OHLX2YWHWA5XXGG","short_pith_number":"pith:GIMYHKSJ","canonical_record":{"source":{"id":"2605.28456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T13:22:08Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"5f1800b07298735af9d0b29bb58999b7b6641ba4de3dc663eca4893f3adb2f45","abstract_canon_sha256":"ea47e2dc3e6b8703ab03bf11d3ca4bf269674b5b503e7f463345d3d230eac4f5"},"schema_version":"1.0"},"canonical_sha256":"321983aa49c97ce3aefac58f6076f731af4e39ec9f3b166ac294592be82b3cff","source":{"kind":"arxiv","id":"2605.28456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28456","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28456v1","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28456","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"GIMYHKSJZF6O","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"GIMYHKSJZF6OHLX2","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"GIMYHKSJ","created_at":"2026-05-28T02:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GIMYHKSJZF6OHLX2YWHWA5XXGG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T13:22:08Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"5f1800b07298735af9d0b29bb58999b7b6641ba4de3dc663eca4893f3adb2f45","abstract_canon_sha256":"ea47e2dc3e6b8703ab03bf11d3ca4bf269674b5b503e7f463345d3d230eac4f5"},"schema_version":"1.0"},"canonical_sha256":"321983aa49c97ce3aefac58f6076f731af4e39ec9f3b166ac294592be82b3cff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:53.551155Z","signature_b64":"vssPXqWxo6XVN1pFUj1zKVGUCSP6GehgIpOKQNjpLEP6j0sW79Yd1wMNzqsoIFnZIUZhyNjzVowaVfYu1qj0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"321983aa49c97ce3aefac58f6076f731af4e39ec9f3b166ac294592be82b3cff","last_reissued_at":"2026-05-28T02:04:53.550659Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:53.550659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28456","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":"2026-05-28T02:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAy6hjFaOd/xL5sXl2n4hGjOzgUZrVqbi75sGcyQn0Mj3Xr9nKFSUeB1zN/Es7/7PxQS4D4kXuZuqCDx6SR5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T07:22:50.805688Z"},"content_sha256":"f9c187a67e8b6b08565b9df5e488df0bee597666e454a6908ee8b6126dafa014","schema_version":"1.0","event_id":"sha256:f9c187a67e8b6b08565b9df5e488df0bee597666e454a6908ee8b6126dafa014"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GIMYHKSJZF6OHLX2YWHWA5XXGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Large Language Models for Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.AI","authors_text":"Chae Won Kim, Hyeongseop Rha, Jeong Hun Yeo, Yong Man Ro","submitted_at":"2026-05-27T13:22:08Z","abstract_excerpt":"Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the best of our knowledge, the first Diffusion Large Language Model (DLLM)-based VSR framework, formulating transcription as iterative masked denoising with flexible-order decoding. With confidence-based unmasking, DLLM-VSR commits high-confidence positions early and uses the committed tokens as bidirectional context to refine ambiguous ones. To adapt DLLMs to VSR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28456","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/2605.28456/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":"2026-05-28T02:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Adbtc42Jb/0d+rUjZ6iaC0BBv0EBN7rnTKdDglHndMMl0Uh1rjpzt5kJC6YydtihH+ucMtKpMuOpI0LdnkipDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T07:22:50.806079Z"},"content_sha256":"b24282ed173c8d097a579a08f1f7cbcdc4da80f50f6c3d33471f12d23a34b11a","schema_version":"1.0","event_id":"sha256:b24282ed173c8d097a579a08f1f7cbcdc4da80f50f6c3d33471f12d23a34b11a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG/bundle.json","state_url":"https://pith.science/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG/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":"2026-06-20T07:22:50Z","links":{"resolver":"https://pith.science/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG","bundle":"https://pith.science/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG/bundle.json","state":"https://pith.science/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GIMYHKSJZF6OHLX2YWHWA5XXGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GIMYHKSJZF6OHLX2YWHWA5XXGG","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":"ea47e2dc3e6b8703ab03bf11d3ca4bf269674b5b503e7f463345d3d230eac4f5","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T13:22:08Z","title_canon_sha256":"5f1800b07298735af9d0b29bb58999b7b6641ba4de3dc663eca4893f3adb2f45"},"schema_version":"1.0","source":{"id":"2605.28456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28456","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28456v1","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28456","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"GIMYHKSJZF6O","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"GIMYHKSJZF6OHLX2","created_at":"2026-05-28T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"GIMYHKSJ","created_at":"2026-05-28T02:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:b24282ed173c8d097a579a08f1f7cbcdc4da80f50f6c3d33471f12d23a34b11a","target":"graph","created_at":"2026-05-28T02:04:53Z","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/2605.28456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the best of our knowledge, the first Diffusion Large Language Model (DLLM)-based VSR framework, formulating transcription as iterative masked denoising with flexible-order decoding. With confidence-based unmasking, DLLM-VSR commits high-confidence positions early and uses the committed tokens as bidirectional context to refine ambiguous ones. To adapt DLLMs to VSR","authors_text":"Chae Won Kim, Hyeongseop Rha, Jeong Hun Yeo, Yong Man Ro","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T13:22:08Z","title":"Diffusion Large Language Models for Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28456","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:f9c187a67e8b6b08565b9df5e488df0bee597666e454a6908ee8b6126dafa014","target":"record","created_at":"2026-05-28T02:04:53Z","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":"ea47e2dc3e6b8703ab03bf11d3ca4bf269674b5b503e7f463345d3d230eac4f5","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T13:22:08Z","title_canon_sha256":"5f1800b07298735af9d0b29bb58999b7b6641ba4de3dc663eca4893f3adb2f45"},"schema_version":"1.0","source":{"id":"2605.28456","kind":"arxiv","version":1}},"canonical_sha256":"321983aa49c97ce3aefac58f6076f731af4e39ec9f3b166ac294592be82b3cff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"321983aa49c97ce3aefac58f6076f731af4e39ec9f3b166ac294592be82b3cff","first_computed_at":"2026-05-28T02:04:53.550659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:53.550659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vssPXqWxo6XVN1pFUj1zKVGUCSP6GehgIpOKQNjpLEP6j0sW79Yd1wMNzqsoIFnZIUZhyNjzVowaVfYu1qj0Cg==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:53.551155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9c187a67e8b6b08565b9df5e488df0bee597666e454a6908ee8b6126dafa014","sha256:b24282ed173c8d097a579a08f1f7cbcdc4da80f50f6c3d33471f12d23a34b11a"],"state_sha256":"86020ebdee0cfc79c055e2262f9a55d0388155bbb097e95e4330978b78798977"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06Qndv3vqrvQHvxBvx8DVh8XA2yAr5IMVQGNHpo2wwfP8jkEgXm5zWtjQC4N0vqaECq27LTzwQ2uGWlYwz4HAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T07:22:50.808207Z","bundle_sha256":"31b66f63a144aa68520af371589f4f6dfe399ad444cf93ada352f440b216f12c"}}