{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KN6WJS7QND3C2IXIKXJ35XT7KH","short_pith_number":"pith:KN6WJS7Q","canonical_record":{"source":{"id":"2111.00610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:48:30Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"10f92294f0a69e638a47448dc518b1f754be37cf4526f278b6c64280b8347a84","abstract_canon_sha256":"7696498449fc1a0507064e49933bd3b703048864be071846bf2fc1c4d93ca94c"},"schema_version":"1.0"},"canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","source":{"kind":"arxiv","id":"2111.00610","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00610","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00610v1","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00610","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"pith_short_12","alias_value":"KN6WJS7QND3C","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"pith_short_16","alias_value":"KN6WJS7QND3C2IXI","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"pith_short_8","alias_value":"KN6WJS7Q","created_at":"2026-07-05T03:27:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KN6WJS7QND3C2IXIKXJ35XT7KH","target":"record","payload":{"canonical_record":{"source":{"id":"2111.00610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:48:30Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"10f92294f0a69e638a47448dc518b1f754be37cf4526f278b6c64280b8347a84","abstract_canon_sha256":"7696498449fc1a0507064e49933bd3b703048864be071846bf2fc1c4d93ca94c"},"schema_version":"1.0"},"canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:44.898765Z","signature_b64":"p2DaDUtuzA77JZUKjY1FMC4KLqorEQa/LokTXrL/DqDNXV4q8AMBnbe6uItbfiA2cvy40z6vUOpup4TIxi1rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","last_reissued_at":"2026-07-05T03:27:44.898221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:44.898221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.00610","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":"2026-07-05T03:27:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PoovhePJZUZTN2DEaDm7TdWTy07Loq/pVQ/fYDb1ifd/fTF48z5Wr6MDlIDq2kR2+jkQv7oj1sIDqvHkgsNNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:53:30.842700Z"},"content_sha256":"a0ea67c3768f9013f0ce284832ec62d4fc7e0cac9d4d294550686b279690328c","schema_version":"1.0","event_id":"sha256:a0ea67c3768f9013f0ce284832ec62d4fc7e0cac9d4d294550686b279690328c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KN6WJS7QND3C2IXIKXJ35XT7KH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W Black, Anurag Katakkar","submitted_at":"2021-10-31T22:48:30Z","abstract_excerpt":"Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with traditional speech LMs often depending on auxiliary text LMs for learning distributional aspects of the language. For the English language, these LMs treat words as atomic units, which presents inherent challenges to language modelling in the speech domain. In this paper, we propose a novel LSTM-based generative speech LM that is inspired by the CBOW model an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00610","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/2111.00610/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":"2026-07-05T03:27:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ko0JeQU15vKumIYxzGig7U80GdARiMqjUNxoZrKmVafUYeDIHKWfl0OGOwh8F+AmSOjLfHIVWP3mtxHRZXdCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:53:30.843080Z"},"content_sha256":"f2beaac48fa2e91fe9994391ab5b1a8368e950c35d9161be92ceaf676802d21d","schema_version":"1.0","event_id":"sha256:f2beaac48fa2e91fe9994391ab5b1a8368e950c35d9161be92ceaf676802d21d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/bundle.json","state_url":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/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":"2026-07-12T14:53:30Z","links":{"resolver":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH","bundle":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/bundle.json","state":"https://pith.science/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KN6WJS7QND3C2IXIKXJ35XT7KH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KN6WJS7QND3C2IXIKXJ35XT7KH","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":"7696498449fc1a0507064e49933bd3b703048864be071846bf2fc1c4d93ca94c","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:48:30Z","title_canon_sha256":"10f92294f0a69e638a47448dc518b1f754be37cf4526f278b6c64280b8347a84"},"schema_version":"1.0","source":{"id":"2111.00610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00610","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00610v1","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00610","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"pith_short_12","alias_value":"KN6WJS7QND3C","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"pith_short_16","alias_value":"KN6WJS7QND3C2IXI","created_at":"2026-07-05T03:27:44Z"},{"alias_kind":"pith_short_8","alias_value":"KN6WJS7Q","created_at":"2026-07-05T03:27:44Z"}],"graph_snapshots":[{"event_id":"sha256:f2beaac48fa2e91fe9994391ab5b1a8368e950c35d9161be92ceaf676802d21d","target":"graph","created_at":"2026-07-05T03:27:44Z","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/2111.00610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with traditional speech LMs often depending on auxiliary text LMs for learning distributional aspects of the language. For the English language, these LMs treat words as atomic units, which presents inherent challenges to language modelling in the speech domain. In this paper, we propose a novel LSTM-based generative speech LM that is inspired by the CBOW model an","authors_text":"Alan W Black, Anurag Katakkar","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:48:30Z","title":"Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00610","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:a0ea67c3768f9013f0ce284832ec62d4fc7e0cac9d4d294550686b279690328c","target":"record","created_at":"2026-07-05T03:27:44Z","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":"7696498449fc1a0507064e49933bd3b703048864be071846bf2fc1c4d93ca94c","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T22:48:30Z","title_canon_sha256":"10f92294f0a69e638a47448dc518b1f754be37cf4526f278b6c64280b8347a84"},"schema_version":"1.0","source":{"id":"2111.00610","kind":"arxiv","version":1}},"canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"537d64cbf068f62d22e855d3bede7f51e82a3a319a7685074086109d4d20b7da","first_computed_at":"2026-07-05T03:27:44.898221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:44.898221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p2DaDUtuzA77JZUKjY1FMC4KLqorEQa/LokTXrL/DqDNXV4q8AMBnbe6uItbfiA2cvy40z6vUOpup4TIxi1rAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:44.898765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0ea67c3768f9013f0ce284832ec62d4fc7e0cac9d4d294550686b279690328c","sha256:f2beaac48fa2e91fe9994391ab5b1a8368e950c35d9161be92ceaf676802d21d"],"state_sha256":"6c6961f077fc00284463d4d01437fa64128ded78384504eacf58287e2d7b6a86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcIHliXBvTZDeWM4iJdRiP9Daer8XD4Oz+A8hq10BdIaV9CuC7lcx6RicaLWuVWSaQnvE88+TiPU9Hd+oEC3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T14:53:30.846784Z","bundle_sha256":"4bf593c62d76154a71809a28b4c8941dc3bdf04c499f5166fa4b835815b83bfe"}}