{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EG55BADKKLUTAGDSXQV4Q4K5ZN","short_pith_number":"pith:EG55BADK","canonical_record":{"source":{"id":"2306.03482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T08:08:18Z","cross_cats_sorted":[],"title_canon_sha256":"22804ecd798eacc1d2002082bd3c9fa5602a4354e592f2ac0e86787f299bc8c3","abstract_canon_sha256":"dd471028d5d9785e120389c7989af5df7efa8ad1f29651101cb9864c662051aa"},"schema_version":"1.0"},"canonical_sha256":"21bbd0806a52e9301872bc2bc8715dcb40a40de576e1c59b390f5b37582b5c63","source":{"kind":"arxiv","id":"2306.03482","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03482","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03482v1","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03482","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"EG55BADKKLUT","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"EG55BADKKLUTAGDS","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"EG55BADK","created_at":"2026-07-05T06:17:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EG55BADKKLUTAGDSXQV4Q4K5ZN","target":"record","payload":{"canonical_record":{"source":{"id":"2306.03482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T08:08:18Z","cross_cats_sorted":[],"title_canon_sha256":"22804ecd798eacc1d2002082bd3c9fa5602a4354e592f2ac0e86787f299bc8c3","abstract_canon_sha256":"dd471028d5d9785e120389c7989af5df7efa8ad1f29651101cb9864c662051aa"},"schema_version":"1.0"},"canonical_sha256":"21bbd0806a52e9301872bc2bc8715dcb40a40de576e1c59b390f5b37582b5c63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:58.577791Z","signature_b64":"gR+yABdEFdoD52tkfuLN/lHKiZHtBTjhDpsGZX/IGJqSsIFWW0ftcj4OWrGLW/lCc4ntL0SeGstG4489K1PKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21bbd0806a52e9301872bc2bc8715dcb40a40de576e1c59b390f5b37582b5c63","last_reissued_at":"2026-07-05T06:17:58.577331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:58.577331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.03482","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":"2026-07-05T06:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RcwHwQf/NM49x6nO9L9VahXes8gGctuXn/j11Xjir0lf6jzpARaxEDj/5NJ0VeYvx4TyNVVtm1Ix9PWLoPeyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:05:20.084213Z"},"content_sha256":"36141c757ff684476ec8f99a1a22816b3e68e9dcf8d394d7243e6faa1e6ab4df","schema_version":"1.0","event_id":"sha256:36141c757ff684476ec8f99a1a22816b3e68e9dcf8d394d7243e6faa1e6ab4df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EG55BADKKLUTAGDSXQV4Q4K5ZN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Looking and Listening: Audio Guided Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Yang, Deqiang Jiang, Enming Zhang, Mingyu Liu, Wenwen Yu, Xiang Bai, Xing Sun, Yuliang Liu","submitted_at":"2023-06-06T08:08:18Z","abstract_excerpt":"Text recognition in the wild is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest vision and language processing are effective for scene text recognition. Yet, solving edit errors such as add, delete, or replace is still the main challenge for existing approaches. In fact, the content of the text and its audio are naturally corresponding to each other, i.e., a single character error may result in a clear different pronunciation. In this paper, we propose the AudioOCR, a simple yet effective probabilistic audio decoder for mel spectrogram seq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03482","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/2306.03482/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":"2026-07-05T06:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCWrSi2eIocid9cI/DBz2yDZplF39ZnI4XA5uJMLhcqoE3qYv75/qwBrtZ2FHBeYfjlKPF690D7joXDiksByCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:05:20.084833Z"},"content_sha256":"fcd97136d3cdfd4f8b7a563e97e4914bf0f5c0b35527fa719b1e957603db1c93","schema_version":"1.0","event_id":"sha256:fcd97136d3cdfd4f8b7a563e97e4914bf0f5c0b35527fa719b1e957603db1c93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN/bundle.json","state_url":"https://pith.science/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN/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":"2026-08-14T03:05:20Z","links":{"resolver":"https://pith.science/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN","bundle":"https://pith.science/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN/bundle.json","state":"https://pith.science/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EG55BADKKLUTAGDSXQV4Q4K5ZN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EG55BADKKLUTAGDSXQV4Q4K5ZN","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":"dd471028d5d9785e120389c7989af5df7efa8ad1f29651101cb9864c662051aa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T08:08:18Z","title_canon_sha256":"22804ecd798eacc1d2002082bd3c9fa5602a4354e592f2ac0e86787f299bc8c3"},"schema_version":"1.0","source":{"id":"2306.03482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03482","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03482v1","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03482","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"EG55BADKKLUT","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"EG55BADKKLUTAGDS","created_at":"2026-07-05T06:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"EG55BADK","created_at":"2026-07-05T06:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:fcd97136d3cdfd4f8b7a563e97e4914bf0f5c0b35527fa719b1e957603db1c93","target":"graph","created_at":"2026-07-05T06:17:58Z","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/2306.03482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text recognition in the wild is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest vision and language processing are effective for scene text recognition. Yet, solving edit errors such as add, delete, or replace is still the main challenge for existing approaches. In fact, the content of the text and its audio are naturally corresponding to each other, i.e., a single character error may result in a clear different pronunciation. In this paper, we propose the AudioOCR, a simple yet effective probabilistic audio decoder for mel spectrogram seq","authors_text":"Biao Yang, Deqiang Jiang, Enming Zhang, Mingyu Liu, Wenwen Yu, Xiang Bai, Xing Sun, Yuliang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T08:08:18Z","title":"Looking and Listening: Audio Guided Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03482","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":"sha256:36141c757ff684476ec8f99a1a22816b3e68e9dcf8d394d7243e6faa1e6ab4df","target":"record","created_at":"2026-07-05T06:17:58Z","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":"dd471028d5d9785e120389c7989af5df7efa8ad1f29651101cb9864c662051aa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T08:08:18Z","title_canon_sha256":"22804ecd798eacc1d2002082bd3c9fa5602a4354e592f2ac0e86787f299bc8c3"},"schema_version":"1.0","source":{"id":"2306.03482","kind":"arxiv","version":1}},"canonical_sha256":"21bbd0806a52e9301872bc2bc8715dcb40a40de576e1c59b390f5b37582b5c63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21bbd0806a52e9301872bc2bc8715dcb40a40de576e1c59b390f5b37582b5c63","first_computed_at":"2026-07-05T06:17:58.577331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:58.577331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gR+yABdEFdoD52tkfuLN/lHKiZHtBTjhDpsGZX/IGJqSsIFWW0ftcj4OWrGLW/lCc4ntL0SeGstG4489K1PKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:58.577791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36141c757ff684476ec8f99a1a22816b3e68e9dcf8d394d7243e6faa1e6ab4df","sha256:fcd97136d3cdfd4f8b7a563e97e4914bf0f5c0b35527fa719b1e957603db1c93"],"state_sha256":"41e049dc97fd3a69dc3e46c52e0674c50b6e1a56bf9f3327c7a4b90d6e83759e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6SEUjw/bQDafAMeh/mdkLbH7yaYQC+ekHhZhSCVrP0xQ6vYFBGPMI03GEeD0xqJ5oVe/4hHn5MeStlnNimVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:05:20.090876Z","bundle_sha256":"e36dccd373bf6853cd961e815bfb0a30bb12e186d84e0ab3b226d90ef6d7c987"}}