{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YCGRDQZBUHXUZ7JZQLNM25WG4A","short_pith_number":"pith:YCGRDQZB","canonical_record":{"source":{"id":"2504.07229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T19:09:54Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"5837057b7b124ab7cf6245952c3358b2b713c216edf9368d88b12d458699487f","abstract_canon_sha256":"e017a747fbb153bc0f926acd2637bf2c837141e92b39ca07ffd084bbf0958f80"},"schema_version":"1.0"},"canonical_sha256":"c08d11c321a1ef4cfd3982dacd76c6e036b662e35960e217fd2226a329f8dac9","source":{"kind":"arxiv","id":"2504.07229","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07229","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07229v1","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07229","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"YCGRDQZBUHXU","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"YCGRDQZBUHXUZ7JZ","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"YCGRDQZB","created_at":"2026-07-05T10:47:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YCGRDQZBUHXUZ7JZQLNM25WG4A","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T19:09:54Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"5837057b7b124ab7cf6245952c3358b2b713c216edf9368d88b12d458699487f","abstract_canon_sha256":"e017a747fbb153bc0f926acd2637bf2c837141e92b39ca07ffd084bbf0958f80"},"schema_version":"1.0"},"canonical_sha256":"c08d11c321a1ef4cfd3982dacd76c6e036b662e35960e217fd2226a329f8dac9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:05.459613Z","signature_b64":"+/rdwJFCMsdPTWUTVqGgTKUW8opn+dpvM29hYk/wklDOUypxdOV3j5La/4SZem2ae0NXrYx0jpEREhvUu77MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c08d11c321a1ef4cfd3982dacd76c6e036b662e35960e217fd2226a329f8dac9","last_reissued_at":"2026-07-05T10:47:05.459164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:05.459164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07229","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":"2026-07-05T10:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijrF+5ctyA/TX799YctieCJBtml9O66Zxaj7FBjnqu2RZJ3jJUJ5kC5GIC0H7gc/T/nJZHIwBHg8WUUWNUFjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:53:30.030855Z"},"content_sha256":"26c6bf7e59c961e4bf5bee61203b066f2842367de99153b550bb9d823e725487","schema_version":"1.0","event_id":"sha256:26c6bf7e59c961e4bf5bee61203b066f2842367de99153b550bb9d823e725487"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YCGRDQZBUHXUZ7JZQLNM25WG4A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual-Aware Speech Recognition for Noisy Scenarios","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.CL","authors_text":"Karan Singla, Lakshmipathi Balaji","submitted_at":"2025-04-09T19:09:54Z","abstract_excerpt":"Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech Recognition (AVSR) models often struggle in noisy scenarios. To solve this task, we propose a model that improves transcription by correlating noise sources to visual cues. Unlike works that rely on lip motion and require the speaker's visibility, we exploit broader visual information from the environment. This allows our model to naturally filter speech from noise "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07229","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/2504.07229/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":"2026-07-05T10:47:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UtPtHq9Qhpsi87Y8aZCZe56MMfiTORRatcE6YJQMfWTyuCpdKKCgb6PQoqoVWV/6P0tjGKWKsPtKK7USGT2wBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:53:30.031376Z"},"content_sha256":"53a947a12984cf27dde7366f393bdf781d91344ca7960c74a5c5e9d02cce3a21","schema_version":"1.0","event_id":"sha256:53a947a12984cf27dde7366f393bdf781d91344ca7960c74a5c5e9d02cce3a21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A/bundle.json","state_url":"https://pith.science/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A/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":"2026-08-19T10:53:30Z","links":{"resolver":"https://pith.science/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A","bundle":"https://pith.science/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A/bundle.json","state":"https://pith.science/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCGRDQZBUHXUZ7JZQLNM25WG4A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YCGRDQZBUHXUZ7JZQLNM25WG4A","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":"e017a747fbb153bc0f926acd2637bf2c837141e92b39ca07ffd084bbf0958f80","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T19:09:54Z","title_canon_sha256":"5837057b7b124ab7cf6245952c3358b2b713c216edf9368d88b12d458699487f"},"schema_version":"1.0","source":{"id":"2504.07229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07229","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07229v1","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07229","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"pith_short_12","alias_value":"YCGRDQZBUHXU","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"pith_short_16","alias_value":"YCGRDQZBUHXUZ7JZ","created_at":"2026-07-05T10:47:05Z"},{"alias_kind":"pith_short_8","alias_value":"YCGRDQZB","created_at":"2026-07-05T10:47:05Z"}],"graph_snapshots":[{"event_id":"sha256:53a947a12984cf27dde7366f393bdf781d91344ca7960c74a5c5e9d02cce3a21","target":"graph","created_at":"2026-07-05T10:47:05Z","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/2504.07229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech Recognition (AVSR) models often struggle in noisy scenarios. To solve this task, we propose a model that improves transcription by correlating noise sources to visual cues. Unlike works that rely on lip motion and require the speaker's visibility, we exploit broader visual information from the environment. This allows our model to naturally filter speech from noise ","authors_text":"Karan Singla, Lakshmipathi Balaji","cross_cats":["eess.AS","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T19:09:54Z","title":"Visual-Aware Speech Recognition for Noisy Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07229","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":"sha256:26c6bf7e59c961e4bf5bee61203b066f2842367de99153b550bb9d823e725487","target":"record","created_at":"2026-07-05T10:47:05Z","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":"e017a747fbb153bc0f926acd2637bf2c837141e92b39ca07ffd084bbf0958f80","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T19:09:54Z","title_canon_sha256":"5837057b7b124ab7cf6245952c3358b2b713c216edf9368d88b12d458699487f"},"schema_version":"1.0","source":{"id":"2504.07229","kind":"arxiv","version":1}},"canonical_sha256":"c08d11c321a1ef4cfd3982dacd76c6e036b662e35960e217fd2226a329f8dac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c08d11c321a1ef4cfd3982dacd76c6e036b662e35960e217fd2226a329f8dac9","first_computed_at":"2026-07-05T10:47:05.459164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:05.459164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+/rdwJFCMsdPTWUTVqGgTKUW8opn+dpvM29hYk/wklDOUypxdOV3j5La/4SZem2ae0NXrYx0jpEREhvUu77MBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:05.459613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26c6bf7e59c961e4bf5bee61203b066f2842367de99153b550bb9d823e725487","sha256:53a947a12984cf27dde7366f393bdf781d91344ca7960c74a5c5e9d02cce3a21"],"state_sha256":"0333d56b5f28182d36c4cdc1d1a9622d0d7a5d6510b3084a3af2377215ee7a4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"khjpYa9aGvmE9Jpf4u2JqrPwE7Ezuz32ay4HOUGJpmd84Yn2BAhmfeQsCyUkS9MwPSSpBAMoYrYq6T7LNKctBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:53:30.036270Z","bundle_sha256":"38ac83f4e30a52f67b148d1623a0f9972e2f98aea7e0762b4679136a03c31143"}}