{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MTZBYOICM4VOH3DN5BOR6SNA6M","short_pith_number":"pith:MTZBYOIC","canonical_record":{"source":{"id":"2506.00267","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T22:03:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bb71c44e2dccc91e90644a6f26c4222911597fcb9f90e9eaa9953b4b5e01beab","abstract_canon_sha256":"7fb291a48cc15f636dc1641d397b942cb869ce263701461c186ce3b4fe1a34dd"},"schema_version":"1.0"},"canonical_sha256":"64f21c3902672ae3ec6de85d1f49a0f339daf989f239aba1ed12b1da5cab6994","source":{"kind":"arxiv","id":"2506.00267","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00267","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00267v3","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00267","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"MTZBYOICM4VO","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"MTZBYOICM4VOH3DN","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"MTZBYOIC","created_at":"2026-07-05T11:19:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MTZBYOICM4VOH3DN5BOR6SNA6M","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00267","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T22:03:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bb71c44e2dccc91e90644a6f26c4222911597fcb9f90e9eaa9953b4b5e01beab","abstract_canon_sha256":"7fb291a48cc15f636dc1641d397b942cb869ce263701461c186ce3b4fe1a34dd"},"schema_version":"1.0"},"canonical_sha256":"64f21c3902672ae3ec6de85d1f49a0f339daf989f239aba1ed12b1da5cab6994","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:27.685836Z","signature_b64":"rD70XR0ZYToJ4q7ZTsl80fnrA4XT14+u4vfi8tEes/Gvl/NKh0uOAfxnGW4EezIWqUtfq97Zfw8K60DydlWSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64f21c3902672ae3ec6de85d1f49a0f339daf989f239aba1ed12b1da5cab6994","last_reissued_at":"2026-07-05T11:19:27.685304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:27.685304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00267","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7bddU1Q4+vXDygiIc57k71Zpu3oLVvARNTJ4ZHNeE61muByV87qbqUNV9nY1gLW75EmkI3nx3pLXx8lM/NqnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:40:34.450793Z"},"content_sha256":"cfaab98540e7e97593d85f170b8a743563e497d1f1e84b6fa1387cb0de2bd52f","schema_version":"1.0","event_id":"sha256:cfaab98540e7e97593d85f170b8a743563e497d1f1e84b6fa1387cb0de2bd52f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MTZBYOICM4VOH3DN5BOR6SNA6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CASPER: A Large Scale Spontaneous Speech Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cihan Xiao, Emmanuel Dupoux, Ethan Poon, Lavanya Shankar, Leibny Paola Garcia Perera, Mehmet Emre Tiryaki, Rong Yang, Ruixing Liang, Sanjeev Khudanpur, Veronica Bae, Xiangyu Zhang","submitted_at":"2025-05-30T22:03:59Z","abstract_excerpt":"The success of large language models has driven interest in developing similar speech processing capabilities. However, a key challenge is the scarcity of high-quality spontaneous speech data, as most existing datasets contain scripted dialogues. To address this, we present a novel pipeline for eliciting and recording natural dialogues and release our dataset with 100+ hours of spontaneous speech. Our approach fosters fluid, natural conversations while encouraging a diverse range of topics and interactive exchanges. Unlike traditional methods, it facilitates genuine interactions, providing a r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00267","kind":"arxiv","version":3},"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/2506.00267/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":"2026-07-05T11:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d59xHtmGG5HrsweV+OcmumsY9/5jHksoP3f31ZBOGw47CJaa9fNv3I8nIwQH92pyOQNOOegKU93Fx3q9+6L9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:40:34.451307Z"},"content_sha256":"975cbf4fda15e98c12fd2a168097806e688f4a939252505f0d961af41f8aa3e7","schema_version":"1.0","event_id":"sha256:975cbf4fda15e98c12fd2a168097806e688f4a939252505f0d961af41f8aa3e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MTZBYOICM4VOH3DN5BOR6SNA6M/bundle.json","state_url":"https://pith.science/pith/MTZBYOICM4VOH3DN5BOR6SNA6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MTZBYOICM4VOH3DN5BOR6SNA6M/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":"2026-08-09T03:40:34Z","links":{"resolver":"https://pith.science/pith/MTZBYOICM4VOH3DN5BOR6SNA6M","bundle":"https://pith.science/pith/MTZBYOICM4VOH3DN5BOR6SNA6M/bundle.json","state":"https://pith.science/pith/MTZBYOICM4VOH3DN5BOR6SNA6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MTZBYOICM4VOH3DN5BOR6SNA6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MTZBYOICM4VOH3DN5BOR6SNA6M","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":"7fb291a48cc15f636dc1641d397b942cb869ce263701461c186ce3b4fe1a34dd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T22:03:59Z","title_canon_sha256":"bb71c44e2dccc91e90644a6f26c4222911597fcb9f90e9eaa9953b4b5e01beab"},"schema_version":"1.0","source":{"id":"2506.00267","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00267","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00267v3","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00267","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"MTZBYOICM4VO","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"MTZBYOICM4VOH3DN","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"MTZBYOIC","created_at":"2026-07-05T11:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:975cbf4fda15e98c12fd2a168097806e688f4a939252505f0d961af41f8aa3e7","target":"graph","created_at":"2026-07-05T11:19:27Z","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/2506.00267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of large language models has driven interest in developing similar speech processing capabilities. However, a key challenge is the scarcity of high-quality spontaneous speech data, as most existing datasets contain scripted dialogues. To address this, we present a novel pipeline for eliciting and recording natural dialogues and release our dataset with 100+ hours of spontaneous speech. Our approach fosters fluid, natural conversations while encouraging a diverse range of topics and interactive exchanges. Unlike traditional methods, it facilitates genuine interactions, providing a r","authors_text":"Cihan Xiao, Emmanuel Dupoux, Ethan Poon, Lavanya Shankar, Leibny Paola Garcia Perera, Mehmet Emre Tiryaki, Rong Yang, Ruixing Liang, Sanjeev Khudanpur, Veronica Bae, Xiangyu Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T22:03:59Z","title":"CASPER: A Large Scale Spontaneous Speech Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00267","kind":"arxiv","version":3},"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:cfaab98540e7e97593d85f170b8a743563e497d1f1e84b6fa1387cb0de2bd52f","target":"record","created_at":"2026-07-05T11:19:27Z","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":"7fb291a48cc15f636dc1641d397b942cb869ce263701461c186ce3b4fe1a34dd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T22:03:59Z","title_canon_sha256":"bb71c44e2dccc91e90644a6f26c4222911597fcb9f90e9eaa9953b4b5e01beab"},"schema_version":"1.0","source":{"id":"2506.00267","kind":"arxiv","version":3}},"canonical_sha256":"64f21c3902672ae3ec6de85d1f49a0f339daf989f239aba1ed12b1da5cab6994","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64f21c3902672ae3ec6de85d1f49a0f339daf989f239aba1ed12b1da5cab6994","first_computed_at":"2026-07-05T11:19:27.685304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:27.685304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rD70XR0ZYToJ4q7ZTsl80fnrA4XT14+u4vfi8tEes/Gvl/NKh0uOAfxnGW4EezIWqUtfq97Zfw8K60DydlWSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:27.685836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00267","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfaab98540e7e97593d85f170b8a743563e497d1f1e84b6fa1387cb0de2bd52f","sha256:975cbf4fda15e98c12fd2a168097806e688f4a939252505f0d961af41f8aa3e7"],"state_sha256":"45211a5c034e0b7bc7ccf054faf77ee837e85809852cd511b2b297605d81554e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"weybeLYsewigo3yJZFXpF8Gcsprv5umYQDO3hFvONZdiNdUrZJj7LjR3mrpceGA9YeVj/LYVh9XXAZGPEm/HAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:40:34.455936Z","bundle_sha256":"24543659805821bc21916f7fb72f63be84549c92d9c42e72c919b0a41a78a619"}}