{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KLEY6SEDKXRZDOHIAV2POITCRD","short_pith_number":"pith:KLEY6SED","canonical_record":{"source":{"id":"2506.22858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:41:36Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fa85fea6c509e0cd2f91efab0aca39edde1918dd98c154e9c574bf7a1f36aa0a","abstract_canon_sha256":"8933158d4e8695aa53da073ef95942c655ffbe1ff41bb7c0199ca6453fdd723d"},"schema_version":"1.0"},"canonical_sha256":"52c98f488355e391b8e80574f7226288f6ea4e6b19b1c4a23126b795446eb730","source":{"kind":"arxiv","id":"2506.22858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22858","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22858v1","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22858","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"KLEY6SEDKXRZ","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"KLEY6SEDKXRZDOHI","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"KLEY6SED","created_at":"2026-07-05T11:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KLEY6SEDKXRZDOHIAV2POITCRD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:41:36Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fa85fea6c509e0cd2f91efab0aca39edde1918dd98c154e9c574bf7a1f36aa0a","abstract_canon_sha256":"8933158d4e8695aa53da073ef95942c655ffbe1ff41bb7c0199ca6453fdd723d"},"schema_version":"1.0"},"canonical_sha256":"52c98f488355e391b8e80574f7226288f6ea4e6b19b1c4a23126b795446eb730","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:46.768291Z","signature_b64":"/4Ne1DEJxaifEbhKG0baYHkuLp/dYjtn6de1c2IhhhPl6SLZsBNdF/ixuEKrK09rDOgwOMNAY9ggJ/ryjM/MCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c98f488355e391b8e80574f7226288f6ea4e6b19b1c4a23126b795446eb730","last_reissued_at":"2026-07-05T11:28:46.767781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:46.767781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22858","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":"2026-07-05T11:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wwfcWfNq1dp/qT76UVApL7Kgnlr9Z5MNZR+GCtxijdZ3IaCddDUPD8wNuWlqzuYnH9rO4+3TC9aztCnqQ8/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:14:18.798757Z"},"content_sha256":"ca779f97d803a0d68a4fb69156335e957d94b554b6ee2f5296443bf341862e20","schema_version":"1.0","event_id":"sha256:ca779f97d803a0d68a4fb69156335e957d94b554b6ee2f5296443bf341862e20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KLEY6SEDKXRZDOHIAV2POITCRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Duygu Altinok","submitted_at":"2025-06-28T11:41:36Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER) and impair semantic understanding in critical domains like legal, financial, and medical applications. We propose a novel training approach that extends the semantic context of ASR models by adding overlapping context windows during training. By sliding 5-second overlaps on both sides of 30-second chunks, we create a 40-second \"effective semantic window,\" i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22858","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/2506.22858/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":"2026-07-05T11:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PGTh/ipiex2XMnp+kHkg0Eunx/GLjZ7UGbFjeg5+vzkSur3XV0pJhvDM6N5sknboEghw8bfc3o4P0tlK9E1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:14:18.799402Z"},"content_sha256":"2e20b9ddad2002f06bff5e11f2e2bb4351738cc9b1e8e8d70f33a90e21548fb4","schema_version":"1.0","event_id":"sha256:2e20b9ddad2002f06bff5e11f2e2bb4351738cc9b1e8e8d70f33a90e21548fb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLEY6SEDKXRZDOHIAV2POITCRD/bundle.json","state_url":"https://pith.science/pith/KLEY6SEDKXRZDOHIAV2POITCRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLEY6SEDKXRZDOHIAV2POITCRD/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":"2026-08-11T02:14:18Z","links":{"resolver":"https://pith.science/pith/KLEY6SEDKXRZDOHIAV2POITCRD","bundle":"https://pith.science/pith/KLEY6SEDKXRZDOHIAV2POITCRD/bundle.json","state":"https://pith.science/pith/KLEY6SEDKXRZDOHIAV2POITCRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLEY6SEDKXRZDOHIAV2POITCRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KLEY6SEDKXRZDOHIAV2POITCRD","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":"8933158d4e8695aa53da073ef95942c655ffbe1ff41bb7c0199ca6453fdd723d","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:41:36Z","title_canon_sha256":"fa85fea6c509e0cd2f91efab0aca39edde1918dd98c154e9c574bf7a1f36aa0a"},"schema_version":"1.0","source":{"id":"2506.22858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22858","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22858v1","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22858","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"KLEY6SEDKXRZ","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"KLEY6SEDKXRZDOHI","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"KLEY6SED","created_at":"2026-07-05T11:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:2e20b9ddad2002f06bff5e11f2e2bb4351738cc9b1e8e8d70f33a90e21548fb4","target":"graph","created_at":"2026-07-05T11:28:46Z","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/2506.22858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER) and impair semantic understanding in critical domains like legal, financial, and medical applications. We propose a novel training approach that extends the semantic context of ASR models by adding overlapping context windows during training. By sliding 5-second overlaps on both sides of 30-second chunks, we create a 40-second \"effective semantic window,\" i","authors_text":"Duygu Altinok","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:41:36Z","title":"Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22858","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:ca779f97d803a0d68a4fb69156335e957d94b554b6ee2f5296443bf341862e20","target":"record","created_at":"2026-07-05T11:28:46Z","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":"8933158d4e8695aa53da073ef95942c655ffbe1ff41bb7c0199ca6453fdd723d","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T11:41:36Z","title_canon_sha256":"fa85fea6c509e0cd2f91efab0aca39edde1918dd98c154e9c574bf7a1f36aa0a"},"schema_version":"1.0","source":{"id":"2506.22858","kind":"arxiv","version":1}},"canonical_sha256":"52c98f488355e391b8e80574f7226288f6ea4e6b19b1c4a23126b795446eb730","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52c98f488355e391b8e80574f7226288f6ea4e6b19b1c4a23126b795446eb730","first_computed_at":"2026-07-05T11:28:46.767781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:46.767781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4Ne1DEJxaifEbhKG0baYHkuLp/dYjtn6de1c2IhhhPl6SLZsBNdF/ixuEKrK09rDOgwOMNAY9ggJ/ryjM/MCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:46.768291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca779f97d803a0d68a4fb69156335e957d94b554b6ee2f5296443bf341862e20","sha256:2e20b9ddad2002f06bff5e11f2e2bb4351738cc9b1e8e8d70f33a90e21548fb4"],"state_sha256":"9f6b7bc911e0dcafa077c3f451e9a18cf5074851deeae76729665c26fb8c8baa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2SVLqrUtq2w6rEpT6/7uETpz0qzyr9u4Crb6ru5kUI9nAXVahPABwtLyjzhLxoE/RvGL5ucx7fQ6NRsXRuHVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:14:18.811420Z","bundle_sha256":"d2971e6dd9bee5903eec15e797ae177942a8120a145ffbec4f0cc4803e964357"}}