{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IPLU4GTM7KQMNUTHQ23CLJ63ZY","short_pith_number":"pith:IPLU4GTM","schema_version":"1.0","canonical_sha256":"43d74e1a6cfaa0c6d26786b625a7dbce13fe61f4cba9be6ce5844a4432050792","source":{"kind":"arxiv","id":"2606.24889","version":1},"attestation_state":"computed","paper":{"title":"Graph-Based Phonetic Error Correction of Noisy ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Aneesh Mukkamala, Mohammadi Zaki, Pankaj Wasnik, Pratik Rakesh Singh","submitted_at":"2026-04-29T13:57:11Z","abstract_excerpt":"Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semantically critical tokens such as named entities, negations, and sentiment-bearing words. These errors are often structured, arising from phonetic similarity rather than random noise, making naive token-level correction insufficient. We propose a structured ASR correction framework, that we call G-SPIN, that combines phonetic graph modeling with contextual language understanding. A graph neural network (GNN) first constructs acoustically plausible "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.24889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-29T13:57:11Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f0bbb49f335097955aef98671ab483b43c460cd7cf40d694a0fb86a744e1bb5c","abstract_canon_sha256":"5f918c6cd1df18c9964644ebdc816286224110bde537b8bea956fbadd21152f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:17:45.241255Z","signature_b64":"N6y3ZtsXxcHFxaKRrcCuKoQfyYEaHCM+cnsxE3Gy7k64631dixoHyLi+r0qNTxRMPmhTPXhOysaggLU1fXTKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43d74e1a6cfaa0c6d26786b625a7dbce13fe61f4cba9be6ce5844a4432050792","last_reissued_at":"2026-06-25T00:17:45.240756Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:17:45.240756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Based Phonetic Error Correction of Noisy ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Aneesh Mukkamala, Mohammadi Zaki, Pankaj Wasnik, Pratik Rakesh Singh","submitted_at":"2026-04-29T13:57:11Z","abstract_excerpt":"Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semantically critical tokens such as named entities, negations, and sentiment-bearing words. These errors are often structured, arising from phonetic similarity rather than random noise, making naive token-level correction insufficient. We propose a structured ASR correction framework, that we call G-SPIN, that combines phonetic graph modeling with contextual language understanding. A graph neural network (GNN) first constructs acoustically plausible "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24889","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/2606.24889/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.24889","created_at":"2026-06-25T00:17:45.240822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24889v1","created_at":"2026-06-25T00:17:45.240822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24889","created_at":"2026-06-25T00:17:45.240822+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPLU4GTM7KQM","created_at":"2026-06-25T00:17:45.240822+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPLU4GTM7KQMNUTH","created_at":"2026-06-25T00:17:45.240822+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPLU4GTM","created_at":"2026-06-25T00:17:45.240822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY","json":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY.json","graph_json":"https://pith.science/api/pith-number/IPLU4GTM7KQMNUTHQ23CLJ63ZY/graph.json","events_json":"https://pith.science/api/pith-number/IPLU4GTM7KQMNUTHQ23CLJ63ZY/events.json","paper":"https://pith.science/paper/IPLU4GTM"},"agent_actions":{"view_html":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY","download_json":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY.json","view_paper":"https://pith.science/paper/IPLU4GTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24889&json=true","fetch_graph":"https://pith.science/api/pith-number/IPLU4GTM7KQMNUTHQ23CLJ63ZY/graph.json","fetch_events":"https://pith.science/api/pith-number/IPLU4GTM7KQMNUTHQ23CLJ63ZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY/action/storage_attestation","attest_author":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY/action/author_attestation","sign_citation":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY/action/citation_signature","submit_replication":"https://pith.science/pith/IPLU4GTM7KQMNUTHQ23CLJ63ZY/action/replication_record"}},"created_at":"2026-06-25T00:17:45.240822+00:00","updated_at":"2026-06-25T00:17:45.240822+00:00"}