{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TOTUV6A32IZEZZVDHKVWXA5I4D","short_pith_number":"pith:TOTUV6A3","canonical_record":{"source":{"id":"2506.08836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T14:22:48Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"ca3b7225267d2a80723e6e213443d12630804f0472fac72cb711471e88f129eb","abstract_canon_sha256":"5e1836aacf79ea6f7b0f9610ae473d7e898ece133007d16cbefb74c905f0cf67"},"schema_version":"1.0"},"canonical_sha256":"9ba74af81bd2324ce6a33aab6b83a8e0f23dbe2a7059792e11dd1c2660283028","source":{"kind":"arxiv","id":"2506.08836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08836","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08836v1","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08836","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"TOTUV6A32IZE","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"pith_short_16","alias_value":"TOTUV6A32IZEZZVD","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"pith_short_8","alias_value":"TOTUV6A3","created_at":"2026-07-05T11:19:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TOTUV6A32IZEZZVDHKVWXA5I4D","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T14:22:48Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"ca3b7225267d2a80723e6e213443d12630804f0472fac72cb711471e88f129eb","abstract_canon_sha256":"5e1836aacf79ea6f7b0f9610ae473d7e898ece133007d16cbefb74c905f0cf67"},"schema_version":"1.0"},"canonical_sha256":"9ba74af81bd2324ce6a33aab6b83a8e0f23dbe2a7059792e11dd1c2660283028","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:13.938725Z","signature_b64":"cPKSp0gvhe9gNSR2TRifcTq6jSIWhtF3qENaej1m+ewA6OXfdfy/r316dKuVylupQoXhJQiuGBvy6+ehYoxNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba74af81bd2324ce6a33aab6b83a8e0f23dbe2a7059792e11dd1c2660283028","last_reissued_at":"2026-07-05T11:19:13.938330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:13.938330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08836","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":"2026-07-05T11:19:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3C5iZOZznPzZ/7HvhO9Tz51JfPuw3uY7fCFMoJOVG6leyewSjMmljKE3M6ORoxCSA1dXBvhWyY+3RUi9bblHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:56:10.923846Z"},"content_sha256":"1946adec82b8474e98bb36a4aab0eb71b40e7e1e085eb380625d7584c423c122","schema_version":"1.0","event_id":"sha256:1946adec82b8474e98bb36a4aab0eb71b40e7e1e085eb380625d7584c423c122"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TOTUV6A32IZEZZVDHKVWXA5I4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing STT for Low-Resource Real-World Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Flavio D'Intino, Hans-Peter Hutter","submitted_at":"2025-06-10T14:22:48Z","abstract_excerpt":"Swiss German is a low-resource language represented by diverse dialects that differ significantly from Standard German and from each other, lacking a standardized written form. As a result, transcribing Swiss German involves translating into Standard German. Existing datasets have been collected in controlled environments, yielding effective speech-to-text (STT) models, but these models struggle with spontaneous conversational speech.\n  This paper, therefore, introduces the new SRB-300 dataset, a 300-hour annotated speech corpus featuring real-world long-audio recordings from 39 Swiss German r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08836","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/2506.08836/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":"2026-07-05T11:19:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LCc0P/P7zyNfkVeTR7BTaDHlN+9HMOFwaFuNq1bh2hwM7I86x0VN8JXddkWq8nIrl+ywn3MGh8fd/I8234KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:56:10.924336Z"},"content_sha256":"1e6d5ebd83dcf6b07f6c0b05386d236896090f6c2747a5e1f85e20ede1f8e55f","schema_version":"1.0","event_id":"sha256:1e6d5ebd83dcf6b07f6c0b05386d236896090f6c2747a5e1f85e20ede1f8e55f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TOTUV6A32IZEZZVDHKVWXA5I4D/bundle.json","state_url":"https://pith.science/pith/TOTUV6A32IZEZZVDHKVWXA5I4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TOTUV6A32IZEZZVDHKVWXA5I4D/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":"2026-08-22T18:56:10Z","links":{"resolver":"https://pith.science/pith/TOTUV6A32IZEZZVDHKVWXA5I4D","bundle":"https://pith.science/pith/TOTUV6A32IZEZZVDHKVWXA5I4D/bundle.json","state":"https://pith.science/pith/TOTUV6A32IZEZZVDHKVWXA5I4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TOTUV6A32IZEZZVDHKVWXA5I4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TOTUV6A32IZEZZVDHKVWXA5I4D","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":"5e1836aacf79ea6f7b0f9610ae473d7e898ece133007d16cbefb74c905f0cf67","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T14:22:48Z","title_canon_sha256":"ca3b7225267d2a80723e6e213443d12630804f0472fac72cb711471e88f129eb"},"schema_version":"1.0","source":{"id":"2506.08836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08836","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08836v1","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08836","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"TOTUV6A32IZE","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"pith_short_16","alias_value":"TOTUV6A32IZEZZVD","created_at":"2026-07-05T11:19:13Z"},{"alias_kind":"pith_short_8","alias_value":"TOTUV6A3","created_at":"2026-07-05T11:19:13Z"}],"graph_snapshots":[{"event_id":"sha256:1e6d5ebd83dcf6b07f6c0b05386d236896090f6c2747a5e1f85e20ede1f8e55f","target":"graph","created_at":"2026-07-05T11:19:13Z","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/2506.08836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Swiss German is a low-resource language represented by diverse dialects that differ significantly from Standard German and from each other, lacking a standardized written form. As a result, transcribing Swiss German involves translating into Standard German. Existing datasets have been collected in controlled environments, yielding effective speech-to-text (STT) models, but these models struggle with spontaneous conversational speech.\n  This paper, therefore, introduces the new SRB-300 dataset, a 300-hour annotated speech corpus featuring real-world long-audio recordings from 39 Swiss German r","authors_text":"Flavio D'Intino, Hans-Peter Hutter","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T14:22:48Z","title":"Advancing STT for Low-Resource Real-World Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08836","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":"sha256:1946adec82b8474e98bb36a4aab0eb71b40e7e1e085eb380625d7584c423c122","target":"record","created_at":"2026-07-05T11:19:13Z","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":"5e1836aacf79ea6f7b0f9610ae473d7e898ece133007d16cbefb74c905f0cf67","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T14:22:48Z","title_canon_sha256":"ca3b7225267d2a80723e6e213443d12630804f0472fac72cb711471e88f129eb"},"schema_version":"1.0","source":{"id":"2506.08836","kind":"arxiv","version":1}},"canonical_sha256":"9ba74af81bd2324ce6a33aab6b83a8e0f23dbe2a7059792e11dd1c2660283028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ba74af81bd2324ce6a33aab6b83a8e0f23dbe2a7059792e11dd1c2660283028","first_computed_at":"2026-07-05T11:19:13.938330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:13.938330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cPKSp0gvhe9gNSR2TRifcTq6jSIWhtF3qENaej1m+ewA6OXfdfy/r316dKuVylupQoXhJQiuGBvy6+ehYoxNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:13.938725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1946adec82b8474e98bb36a4aab0eb71b40e7e1e085eb380625d7584c423c122","sha256:1e6d5ebd83dcf6b07f6c0b05386d236896090f6c2747a5e1f85e20ede1f8e55f"],"state_sha256":"9869b65836364f35b3fad610e05911764cfaed3a6dc2e89c8994199d90cf3a27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q+K6lRo6K8mJ1arxgKv18bXMrOrYx0O4pZNj3kD+pxV4PhUdNLoryrrFGLfpEI/hM0KfyZUSpNyumuCVExUEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T18:56:10.930816Z","bundle_sha256":"b518a0de7a5723a48a7da8fc724994d4c0d280f69bb195715e2e868a00a448e0"}}