{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2SBOTSAFQUXRN3B7CH3ZP55E5N","short_pith_number":"pith:2SBOTSAF","canonical_record":{"source":{"id":"2110.12561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T00:32:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3f63db4a5c118e123728c6d6042ba33b27c791ef804db9a852361486c6dc7a50","abstract_canon_sha256":"3e944ebc1c3e352dec8f1549e54f825893a427d39e27f23fd9b4f327e32aac53"},"schema_version":"1.0"},"canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","source":{"kind":"arxiv","id":"2110.12561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12561","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12561v1","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12561","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"2SBOTSAFQUXR","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"2SBOTSAFQUXRN3B7","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"2SBOTSAF","created_at":"2026-07-05T03:25:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2SBOTSAFQUXRN3B7CH3ZP55E5N","target":"record","payload":{"canonical_record":{"source":{"id":"2110.12561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T00:32:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3f63db4a5c118e123728c6d6042ba33b27c791ef804db9a852361486c6dc7a50","abstract_canon_sha256":"3e944ebc1c3e352dec8f1549e54f825893a427d39e27f23fd9b4f327e32aac53"},"schema_version":"1.0"},"canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:21.608148Z","signature_b64":"2eQ1DzaqNSuFzCgzuSGuFGZO2uz2QTbDQz2dngA7Aiz4iB6sbRBVc//c8eur6mOVoMmgJT6+d8xEbAQLmBL8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","last_reissued_at":"2026-07-05T03:25:21.607730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:21.607730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.12561","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":"2026-07-05T03:25:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lS69bBLhw61mknMJo2Kl0+BxHgaO4Tgm77CxVVhfzix0rPAkm7wONuCUFzQt8ITYHJfqrTZvxWyCTJL0gRLUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:21:38.895307Z"},"content_sha256":"484d52e5a6ea0c4b43b32954066012436a37a71297d1003b7eda6119f188fa45","schema_version":"1.0","event_id":"sha256:484d52e5a6ea0c4b43b32954066012436a37a71297d1003b7eda6119f188fa45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2SBOTSAFQUXRN3B7CH3ZP55E5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Povey, Jan \"Yenda\" Trmal, Piotr \\.Zelasko, Sanjeev Khudanpur","submitted_at":"2021-10-25T00:32:21Z","abstract_excerpt":"Speech data is notoriously difficult to work with due to a variety of codecs, lengths of recordings, and meta-data formats. We present Lhotse, a speech data representation library that draws upon lessons learned from Kaldi speech recognition toolkit and brings its concepts into the modern deep learning ecosystem. Lhotse provides a common JSON description format with corresponding Python classes and data preparation recipes for over 30 popular speech corpora. Various datasets can be easily combined together and re-purposed for different tasks. The library handles multi-channel recordings, long "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12561","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/2110.12561/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":"2026-07-05T03:25:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7T/vBYZzEB8+ZlT+t9d6TXyFfr37uI3EWM+nlTcAqSY0p5JpGNpkoQZg/7Pgyq+5sv3r6T/HJiCWkfI9wMZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:21:38.895713Z"},"content_sha256":"259c4eb6e63c166821821eb25448f60224162470297d933189bb081949839abe","schema_version":"1.0","event_id":"sha256:259c4eb6e63c166821821eb25448f60224162470297d933189bb081949839abe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/bundle.json","state_url":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/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":"2026-07-07T03:21:38Z","links":{"resolver":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N","bundle":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/bundle.json","state":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2SBOTSAFQUXRN3B7CH3ZP55E5N","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":"3e944ebc1c3e352dec8f1549e54f825893a427d39e27f23fd9b4f327e32aac53","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T00:32:21Z","title_canon_sha256":"3f63db4a5c118e123728c6d6042ba33b27c791ef804db9a852361486c6dc7a50"},"schema_version":"1.0","source":{"id":"2110.12561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12561","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12561v1","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12561","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"2SBOTSAFQUXR","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"2SBOTSAFQUXRN3B7","created_at":"2026-07-05T03:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"2SBOTSAF","created_at":"2026-07-05T03:25:21Z"}],"graph_snapshots":[{"event_id":"sha256:259c4eb6e63c166821821eb25448f60224162470297d933189bb081949839abe","target":"graph","created_at":"2026-07-05T03:25:21Z","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/2110.12561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech data is notoriously difficult to work with due to a variety of codecs, lengths of recordings, and meta-data formats. We present Lhotse, a speech data representation library that draws upon lessons learned from Kaldi speech recognition toolkit and brings its concepts into the modern deep learning ecosystem. Lhotse provides a common JSON description format with corresponding Python classes and data preparation recipes for over 30 popular speech corpora. Various datasets can be easily combined together and re-purposed for different tasks. The library handles multi-channel recordings, long ","authors_text":"Daniel Povey, Jan \"Yenda\" Trmal, Piotr \\.Zelasko, Sanjeev Khudanpur","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T00:32:21Z","title":"Lhotse: a speech data representation library for the modern deep learning ecosystem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12561","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":"sha256:484d52e5a6ea0c4b43b32954066012436a37a71297d1003b7eda6119f188fa45","target":"record","created_at":"2026-07-05T03:25:21Z","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":"3e944ebc1c3e352dec8f1549e54f825893a427d39e27f23fd9b4f327e32aac53","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T00:32:21Z","title_canon_sha256":"3f63db4a5c118e123728c6d6042ba33b27c791ef804db9a852361486c6dc7a50"},"schema_version":"1.0","source":{"id":"2110.12561","kind":"arxiv","version":1}},"canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","first_computed_at":"2026-07-05T03:25:21.607730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:21.607730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2eQ1DzaqNSuFzCgzuSGuFGZO2uz2QTbDQz2dngA7Aiz4iB6sbRBVc//c8eur6mOVoMmgJT6+d8xEbAQLmBL8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:21.608148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:484d52e5a6ea0c4b43b32954066012436a37a71297d1003b7eda6119f188fa45","sha256:259c4eb6e63c166821821eb25448f60224162470297d933189bb081949839abe"],"state_sha256":"57d4e444d4fbe8ba9bda9af46728a998bd0170c6cf8bd55baba3b9fdab10d784"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hb+VIUZpstggQqTuKKGrYsLp9ANtzaWtm3qMAvXzsedJHSdgTRtZXhQXOBE7gozwXBfqNnO4QHlOimBG3IBxAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:21:38.897704Z","bundle_sha256":"f37f7625bd3ac3b83f5692872974bc3933896a56ba504b7e57d2c60ed3fc23de"}}