{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XBA2URIDBICGVQSB65NKOKN3JD","short_pith_number":"pith:XBA2URID","canonical_record":{"source":{"id":"2203.12906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T07:50:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"27843b6a550fcddb5728d9d6bb98f97647f6f73c8c6ec0ebcd8e183abb962315","abstract_canon_sha256":"eaf5082845aa5b456b750dd2cce6154b9e9983800c591321f7ed51271ba15121"},"schema_version":"1.0"},"canonical_sha256":"b841aa45030a046ac241f75aa729bb48dec52016292f186dbc29061f629d5509","source":{"kind":"arxiv","id":"2203.12906","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12906","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12906v1","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12906","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"XBA2URIDBICG","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"XBA2URIDBICGVQSB","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"XBA2URID","created_at":"2026-07-05T04:08:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XBA2URIDBICGVQSB65NKOKN3JD","target":"record","payload":{"canonical_record":{"source":{"id":"2203.12906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T07:50:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"27843b6a550fcddb5728d9d6bb98f97647f6f73c8c6ec0ebcd8e183abb962315","abstract_canon_sha256":"eaf5082845aa5b456b750dd2cce6154b9e9983800c591321f7ed51271ba15121"},"schema_version":"1.0"},"canonical_sha256":"b841aa45030a046ac241f75aa729bb48dec52016292f186dbc29061f629d5509","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:18.711660Z","signature_b64":"WK4IVCiSJ8K1o0LZ3WeLk0JiDNY3MxUl5n4Q+pnd4GyA0qDQSY/Buvz3ApwuHxqS9Vu5vJXbNw6NxY0PCv0RBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b841aa45030a046ac241f75aa729bb48dec52016292f186dbc29061f629d5509","last_reissued_at":"2026-07-05T04:08:18.711190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:18.711190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.12906","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":"2026-07-05T04:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQKFwt01rQg8gM0D7LpAjl1/WFOAF1DAacQS3rEqK1wcTUOYWlOHMOajiMupJxL9kBz2gHON5V+zWCHDi0jbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T22:45:34.874341Z"},"content_sha256":"6a28f0926a86a68d17b2dacf3e00470141a894090690630c99ad82986799efc7","schema_version":"1.0","event_id":"sha256:6a28f0926a86a68d17b2dacf3e00470141a894090690630c99ad82986799efc7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XBA2URIDBICGVQSB65NKOKN3JD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Aku Rouhe, Anja Virkkunen, Anssi Moisio, Dejan Porjazovski, Krister Lind\\'en, Mikko Kurimo, Tam\\'as Gr\\'osz, Yaroslav Getman","submitted_at":"2022-03-24T07:50:25Z","abstract_excerpt":"The Donate Speech campaign has so far succeeded in gathering approximately 3600 hours of ordinary, colloquial Finnish speech into the Lahjoita puhetta (Donate Speech) corpus. The corpus includes over twenty thousand speakers from all the regions of Finland and from all age brackets. The primary goals of the collection were to create a representative, large-scale resource to study spontaneous spoken Finnish and to accelerate the development of language technology and speech-based services. In this paper, we present the collection process and the collected corpus, and showcase its versatility th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12906","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/2203.12906/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":"2026-07-05T04:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MR3WvD6OvTV64B6IQR9iQ5HBZRM5wn4ay8wov06DiVgaSGabxJ2aGXbPja8Qi8x5txh2qt/7jTo0+SRWt445BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T22:45:34.874877Z"},"content_sha256":"3c241342d0666e333882c04e3c7918bae933ad598ff83d61af19bc914eac7f4a","schema_version":"1.0","event_id":"sha256:3c241342d0666e333882c04e3c7918bae933ad598ff83d61af19bc914eac7f4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBA2URIDBICGVQSB65NKOKN3JD/bundle.json","state_url":"https://pith.science/pith/XBA2URIDBICGVQSB65NKOKN3JD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBA2URIDBICGVQSB65NKOKN3JD/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":"2026-08-02T22:45:34Z","links":{"resolver":"https://pith.science/pith/XBA2URIDBICGVQSB65NKOKN3JD","bundle":"https://pith.science/pith/XBA2URIDBICGVQSB65NKOKN3JD/bundle.json","state":"https://pith.science/pith/XBA2URIDBICGVQSB65NKOKN3JD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBA2URIDBICGVQSB65NKOKN3JD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XBA2URIDBICGVQSB65NKOKN3JD","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":"eaf5082845aa5b456b750dd2cce6154b9e9983800c591321f7ed51271ba15121","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T07:50:25Z","title_canon_sha256":"27843b6a550fcddb5728d9d6bb98f97647f6f73c8c6ec0ebcd8e183abb962315"},"schema_version":"1.0","source":{"id":"2203.12906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12906","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12906v1","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12906","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"XBA2URIDBICG","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"XBA2URIDBICGVQSB","created_at":"2026-07-05T04:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"XBA2URID","created_at":"2026-07-05T04:08:18Z"}],"graph_snapshots":[{"event_id":"sha256:3c241342d0666e333882c04e3c7918bae933ad598ff83d61af19bc914eac7f4a","target":"graph","created_at":"2026-07-05T04:08:18Z","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/2203.12906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Donate Speech campaign has so far succeeded in gathering approximately 3600 hours of ordinary, colloquial Finnish speech into the Lahjoita puhetta (Donate Speech) corpus. The corpus includes over twenty thousand speakers from all the regions of Finland and from all age brackets. The primary goals of the collection were to create a representative, large-scale resource to study spontaneous spoken Finnish and to accelerate the development of language technology and speech-based services. In this paper, we present the collection process and the collected corpus, and showcase its versatility th","authors_text":"Aku Rouhe, Anja Virkkunen, Anssi Moisio, Dejan Porjazovski, Krister Lind\\'en, Mikko Kurimo, Tam\\'as Gr\\'osz, Yaroslav Getman","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T07:50:25Z","title":"Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12906","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":"sha256:6a28f0926a86a68d17b2dacf3e00470141a894090690630c99ad82986799efc7","target":"record","created_at":"2026-07-05T04:08:18Z","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":"eaf5082845aa5b456b750dd2cce6154b9e9983800c591321f7ed51271ba15121","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T07:50:25Z","title_canon_sha256":"27843b6a550fcddb5728d9d6bb98f97647f6f73c8c6ec0ebcd8e183abb962315"},"schema_version":"1.0","source":{"id":"2203.12906","kind":"arxiv","version":1}},"canonical_sha256":"b841aa45030a046ac241f75aa729bb48dec52016292f186dbc29061f629d5509","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b841aa45030a046ac241f75aa729bb48dec52016292f186dbc29061f629d5509","first_computed_at":"2026-07-05T04:08:18.711190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:18.711190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WK4IVCiSJ8K1o0LZ3WeLk0JiDNY3MxUl5n4Q+pnd4GyA0qDQSY/Buvz3ApwuHxqS9Vu5vJXbNw6NxY0PCv0RBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:18.711660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.12906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a28f0926a86a68d17b2dacf3e00470141a894090690630c99ad82986799efc7","sha256:3c241342d0666e333882c04e3c7918bae933ad598ff83d61af19bc914eac7f4a"],"state_sha256":"c73a7c63637d2392b1112eb2f126f346a763287fd4111859602ff1eb63bf7f91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CD1QywQc2lZ6m+oa2/Uj5BaCdYUs6nT46E0GOKGtIZoJTtIY/WR577lkMjY807ySe97ZeGrtr/7A4z5IbK8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T22:45:34.880321Z","bundle_sha256":"fa7fbd022edd50f41af244c7364f48f2bd9c3f87e887ff496443795b3bc7046c"}}