{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W36XQHUPNCBDBHPJIRQH24V6EO","short_pith_number":"pith:W36XQHUP","canonical_record":{"source":{"id":"2501.04038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-03T10:51:14Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e6d8f0821433eb30d4b6bb2a6e7736619cdd7a607643dc2b34796adb6a5cb104","abstract_canon_sha256":"dc9160e98b766436c5c4be5de067325bf50f36bb0e0d6ea549e8d591ecc6568b"},"schema_version":"1.0"},"canonical_sha256":"b6fd781e8f6882309de944607d72be239fbf69954f9dece0a66f0e6ed95d91b9","source":{"kind":"arxiv","id":"2501.04038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04038","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04038v1","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04038","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"W36XQHUPNCBD","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"W36XQHUPNCBDBHPJ","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"W36XQHUP","created_at":"2026-07-05T09:58:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W36XQHUPNCBDBHPJIRQH24V6EO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-03T10:51:14Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e6d8f0821433eb30d4b6bb2a6e7736619cdd7a607643dc2b34796adb6a5cb104","abstract_canon_sha256":"dc9160e98b766436c5c4be5de067325bf50f36bb0e0d6ea549e8d591ecc6568b"},"schema_version":"1.0"},"canonical_sha256":"b6fd781e8f6882309de944607d72be239fbf69954f9dece0a66f0e6ed95d91b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:28.838603Z","signature_b64":"mL1/Bt4Z9UTTdWCU47Tiox1ZlJCvE3sDU06Xbrz4+sPgV8ktYhPaNyqwzHWiiHm56EeNzMTphScMxH8DfTpCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6fd781e8f6882309de944607d72be239fbf69954f9dece0a66f0e6ed95d91b9","last_reissued_at":"2026-07-05T09:58:28.838187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:28.838187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04038","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":"2026-07-05T09:58:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGkCGZWH+SvES2C4FO+u9hTcfXgQDxNinCOvR0QypZs7x6J+TFPyM+JZH3xqzNqzNNUxg5inem6wottMVIIaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:03:56.264313Z"},"content_sha256":"3cc2802ac6eabc1068ce4afe10a4147df46df2ec22572574ebea796653b1d78c","schema_version":"1.0","event_id":"sha256:3cc2802ac6eabc1068ce4afe10a4147df46df2ec22572574ebea796653b1d78c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W36XQHUPNCBDBHPJIRQH24V6EO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Haizhou Li, Hongyu Yuan, Rui Liu","submitted_at":"2025-01-03T10:51:14Z","abstract_excerpt":"Unlike traditional Automatic Speech Recognition (ASR), Audio-Visual Speech Recognition (AVSR) takes audio and visual signals simultaneously to infer the transcription. Recent studies have shown that Large Language Models (LLMs) can be effectively used for Generative Error Correction (GER) in ASR by predicting the best transcription from ASR-generated N-best hypotheses. However, these LLMs lack the ability to simultaneously understand audio and visual, making the GER approach challenging to apply in AVSR. In this work, we propose a novel GER paradigm for AVSR, termed AVGER, that follows the con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04038","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/2501.04038/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":"2026-07-05T09:58:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qhma2Oqz8trC/0Pf5nVpOdPsGgGfgoPHdxeZ1y47n905u6pJNqE4jJ8l6cZsP6/Qto3oVoprvqftY8azM+4wDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:03:56.265316Z"},"content_sha256":"62a0e577ee2964f913f3b9aab26f961b81c17d65e81c9fd0119af27b9b159e6c","schema_version":"1.0","event_id":"sha256:62a0e577ee2964f913f3b9aab26f961b81c17d65e81c9fd0119af27b9b159e6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W36XQHUPNCBDBHPJIRQH24V6EO/bundle.json","state_url":"https://pith.science/pith/W36XQHUPNCBDBHPJIRQH24V6EO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W36XQHUPNCBDBHPJIRQH24V6EO/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":"2026-08-15T18:03:56Z","links":{"resolver":"https://pith.science/pith/W36XQHUPNCBDBHPJIRQH24V6EO","bundle":"https://pith.science/pith/W36XQHUPNCBDBHPJIRQH24V6EO/bundle.json","state":"https://pith.science/pith/W36XQHUPNCBDBHPJIRQH24V6EO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W36XQHUPNCBDBHPJIRQH24V6EO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W36XQHUPNCBDBHPJIRQH24V6EO","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":"dc9160e98b766436c5c4be5de067325bf50f36bb0e0d6ea549e8d591ecc6568b","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-03T10:51:14Z","title_canon_sha256":"e6d8f0821433eb30d4b6bb2a6e7736619cdd7a607643dc2b34796adb6a5cb104"},"schema_version":"1.0","source":{"id":"2501.04038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04038","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04038v1","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04038","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"W36XQHUPNCBD","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"W36XQHUPNCBDBHPJ","created_at":"2026-07-05T09:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"W36XQHUP","created_at":"2026-07-05T09:58:28Z"}],"graph_snapshots":[{"event_id":"sha256:62a0e577ee2964f913f3b9aab26f961b81c17d65e81c9fd0119af27b9b159e6c","target":"graph","created_at":"2026-07-05T09:58:28Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.04038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike traditional Automatic Speech Recognition (ASR), Audio-Visual Speech Recognition (AVSR) takes audio and visual signals simultaneously to infer the transcription. Recent studies have shown that Large Language Models (LLMs) can be effectively used for Generative Error Correction (GER) in ASR by predicting the best transcription from ASR-generated N-best hypotheses. However, these LLMs lack the ability to simultaneously understand audio and visual, making the GER approach challenging to apply in AVSR. In this work, we propose a novel GER paradigm for AVSR, termed AVGER, that follows the con","authors_text":"Haizhou Li, Hongyu Yuan, Rui Liu","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-03T10:51:14Z","title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04038","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":"sha256:3cc2802ac6eabc1068ce4afe10a4147df46df2ec22572574ebea796653b1d78c","target":"record","created_at":"2026-07-05T09:58:28Z","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":"dc9160e98b766436c5c4be5de067325bf50f36bb0e0d6ea549e8d591ecc6568b","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-03T10:51:14Z","title_canon_sha256":"e6d8f0821433eb30d4b6bb2a6e7736619cdd7a607643dc2b34796adb6a5cb104"},"schema_version":"1.0","source":{"id":"2501.04038","kind":"arxiv","version":1}},"canonical_sha256":"b6fd781e8f6882309de944607d72be239fbf69954f9dece0a66f0e6ed95d91b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6fd781e8f6882309de944607d72be239fbf69954f9dece0a66f0e6ed95d91b9","first_computed_at":"2026-07-05T09:58:28.838187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:28.838187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mL1/Bt4Z9UTTdWCU47Tiox1ZlJCvE3sDU06Xbrz4+sPgV8ktYhPaNyqwzHWiiHm56EeNzMTphScMxH8DfTpCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:28.838603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cc2802ac6eabc1068ce4afe10a4147df46df2ec22572574ebea796653b1d78c","sha256:62a0e577ee2964f913f3b9aab26f961b81c17d65e81c9fd0119af27b9b159e6c"],"state_sha256":"4988da6485fea5d9a584ef51753219d7b938eababd13a650e1e5a87ba6df11ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gH9CBlm60nwxs+dD8ENaFHCOEgchR9X/PZKkO64OZxF6sob850SzygvhrRvo6NmOF1CdHgXDR8XI4yTeG81Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:03:56.272064Z","bundle_sha256":"1c502d5b2543a267201660521695316b8907343658cb221f684fc414589198d2"}}