{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I7ZRPXNVJHXA2AQC4HYFXROWQV","short_pith_number":"pith:I7ZRPXNV","canonical_record":{"source":{"id":"2405.14259","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T07:39:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c357bda456364c8ee114e5b574fbe30b9806b17a3e26262566a420a9bb8c6d5","abstract_canon_sha256":"bd1288b607665129416402438fc58903729798b28216396856a821bb6505d40a"},"schema_version":"1.0"},"canonical_sha256":"47f317ddb549ee0d0202e1f05bc5d685591d77bf6ee683c29c5e3b6b9a037377","source":{"kind":"arxiv","id":"2405.14259","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14259","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14259v4","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14259","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"I7ZRPXNVJHXA","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"I7ZRPXNVJHXA2AQC","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"I7ZRPXNV","created_at":"2026-07-05T11:19:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I7ZRPXNVJHXA2AQC4HYFXROWQV","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14259","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T07:39:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c357bda456364c8ee114e5b574fbe30b9806b17a3e26262566a420a9bb8c6d5","abstract_canon_sha256":"bd1288b607665129416402438fc58903729798b28216396856a821bb6505d40a"},"schema_version":"1.0"},"canonical_sha256":"47f317ddb549ee0d0202e1f05bc5d685591d77bf6ee683c29c5e3b6b9a037377","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:48.760789Z","signature_b64":"2kHzMyD5vxczisVlWkfTHMeq2PW07YVAa7q2VnCqGpuFkA6bJe8uGC0tRTtD7ywrckUsl+7o5Rrm/LtLUNVBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f317ddb549ee0d0202e1f05bc5d685591d77bf6ee683c29c5e3b6b9a037377","last_reissued_at":"2026-07-05T11:19:48.760191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:48.760191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14259","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+0FUHOr9XAQw5BW+mMzLU6mnu18Zsyig+78xCpaRDdZITAHRXaVah+fqyIqarFyrwYWS7sHFHhB58toSbNcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:22:07.181890Z"},"content_sha256":"726ac8d5847a08580305848f3052059a6d4bc9fac6152ea43436a05a0ae186c2","schema_version":"1.0","event_id":"sha256:726ac8d5847a08580305848f3052059a6d4bc9fac6152ea43436a05a0ae186c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I7ZRPXNVJHXA2AQC4HYFXROWQV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chan-Jan Hsu, Da-shan Shiu, Feng-Ting Liao, Pei-Chen Ho, Po-chun Hsu, Yi-Chang Chen, Yu-Hsiang Wang","submitted_at":"2024-05-23T07:39:42Z","abstract_excerpt":"We propose \"Generative Fusion Decoding\" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for automatic speech recognition (ASR) and optical character recognition (OCR). We derive the necessary formulations to enable GFD to operate across mismatched token spaces of different models by calculating likelihood at the byte level, thereby enabling seamless fusion and synchronous progression during the decoding process. GFD is plug-and-play by design, making it readily compatible with various auto-regressive models wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14259","kind":"arxiv","version":4},"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/2405.14259/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":"2026-07-05T11:19:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzDrkxDXYiFMIq5v/mDictnngW5V6rGmEXU4iq2TEKb9lTIwDN7JFmiiRvC8btYrXnf9vVD76RgMI0BDlTCXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:22:07.182807Z"},"content_sha256":"e8ba62e0614e32c8a7f49580705527f3407caeea6e2dc8bbe35dd72bd816ecee","schema_version":"1.0","event_id":"sha256:e8ba62e0614e32c8a7f49580705527f3407caeea6e2dc8bbe35dd72bd816ecee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV/bundle.json","state_url":"https://pith.science/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV/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":"2026-08-22T15:22:07Z","links":{"resolver":"https://pith.science/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV","bundle":"https://pith.science/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV/bundle.json","state":"https://pith.science/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7ZRPXNVJHXA2AQC4HYFXROWQV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I7ZRPXNVJHXA2AQC4HYFXROWQV","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":"bd1288b607665129416402438fc58903729798b28216396856a821bb6505d40a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T07:39:42Z","title_canon_sha256":"3c357bda456364c8ee114e5b574fbe30b9806b17a3e26262566a420a9bb8c6d5"},"schema_version":"1.0","source":{"id":"2405.14259","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14259","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14259v4","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14259","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"I7ZRPXNVJHXA","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"I7ZRPXNVJHXA2AQC","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"I7ZRPXNV","created_at":"2026-07-05T11:19:48Z"}],"graph_snapshots":[{"event_id":"sha256:e8ba62e0614e32c8a7f49580705527f3407caeea6e2dc8bbe35dd72bd816ecee","target":"graph","created_at":"2026-07-05T11:19:48Z","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/2405.14259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose \"Generative Fusion Decoding\" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for automatic speech recognition (ASR) and optical character recognition (OCR). We derive the necessary formulations to enable GFD to operate across mismatched token spaces of different models by calculating likelihood at the byte level, thereby enabling seamless fusion and synchronous progression during the decoding process. GFD is plug-and-play by design, making it readily compatible with various auto-regressive models wi","authors_text":"Chan-Jan Hsu, Da-shan Shiu, Feng-Ting Liao, Pei-Chen Ho, Po-chun Hsu, Yi-Chang Chen, Yu-Hsiang Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T07:39:42Z","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14259","kind":"arxiv","version":4},"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":"sha256:726ac8d5847a08580305848f3052059a6d4bc9fac6152ea43436a05a0ae186c2","target":"record","created_at":"2026-07-05T11:19:48Z","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":"bd1288b607665129416402438fc58903729798b28216396856a821bb6505d40a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T07:39:42Z","title_canon_sha256":"3c357bda456364c8ee114e5b574fbe30b9806b17a3e26262566a420a9bb8c6d5"},"schema_version":"1.0","source":{"id":"2405.14259","kind":"arxiv","version":4}},"canonical_sha256":"47f317ddb549ee0d0202e1f05bc5d685591d77bf6ee683c29c5e3b6b9a037377","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47f317ddb549ee0d0202e1f05bc5d685591d77bf6ee683c29c5e3b6b9a037377","first_computed_at":"2026-07-05T11:19:48.760191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:48.760191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2kHzMyD5vxczisVlWkfTHMeq2PW07YVAa7q2VnCqGpuFkA6bJe8uGC0tRTtD7ywrckUsl+7o5Rrm/LtLUNVBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:48.760789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14259","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:726ac8d5847a08580305848f3052059a6d4bc9fac6152ea43436a05a0ae186c2","sha256:e8ba62e0614e32c8a7f49580705527f3407caeea6e2dc8bbe35dd72bd816ecee"],"state_sha256":"ee7b27461291af43971f706ce5f184223221a741278505ce9abf6ced83b56809"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3JO61v03WjbisBiFrbIaFLQ8iJ+A4frXz7TsW6uCq58BPb1aPLM9tneDMiLsGsoqf2XMvAVhhCtiosC/1tEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:22:07.187355Z","bundle_sha256":"6e6897ddac82bba02bb03ec430e609c061d776ecf5c507b7ef782fdd68def994"}}