{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:F7L6IUPJDFN5GPJNLUU3UMREHW","short_pith_number":"pith:F7L6IUPJ","canonical_record":{"source":{"id":"1603.02845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-09T11:14:23Z","cross_cats_sorted":[],"title_canon_sha256":"13d9355f5043dce98fd539051528d0dc73bcf3449c65563ae2adc1cc1e488042","abstract_canon_sha256":"603902fae8bd092db007bf99bdc7023b3d4564ad77a2165ee7826b3342fe0e7d"},"schema_version":"1.0"},"canonical_sha256":"2fd7e451e9195bd33d2d5d29ba32243db48af3598f3d957b09651c5ce903c24e","source":{"kind":"arxiv","id":"1603.02845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.02845","created_at":"2026-05-18T01:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"1603.02845v1","created_at":"2026-05-18T01:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02845","created_at":"2026-05-18T01:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"F7L6IUPJDFN5","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"F7L6IUPJDFN5GPJN","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"F7L6IUPJ","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:F7L6IUPJDFN5GPJNLUU3UMREHW","target":"record","payload":{"canonical_record":{"source":{"id":"1603.02845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-09T11:14:23Z","cross_cats_sorted":[],"title_canon_sha256":"13d9355f5043dce98fd539051528d0dc73bcf3449c65563ae2adc1cc1e488042","abstract_canon_sha256":"603902fae8bd092db007bf99bdc7023b3d4564ad77a2165ee7826b3342fe0e7d"},"schema_version":"1.0"},"canonical_sha256":"2fd7e451e9195bd33d2d5d29ba32243db48af3598f3d957b09651c5ce903c24e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:19.735210Z","signature_b64":"qOMC2lIC3iUiv2xbN8R5bVx45X36rl6NeZQsDruqGHmZHe1QE529U3wOVxUuMHb5El2yy0NjO8YeZw25uGMdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fd7e451e9195bd33d2d5d29ba32243db48af3598f3d957b09651c5ce903c24e","last_reissued_at":"2026-05-18T01:19:19.734682Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:19.734682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.02845","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":"2026-05-18T01:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6d9fp/0zN/RJtno/WZWeotuCBF7iMusc5P89BqEIdMlRj+Eb1E/BGPi6ArMaHiuGeMlrqY7tJP1zeX2pSA1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:29:57.480834Z"},"content_sha256":"fde312850e30636458f67cb42e40ba4029fcc39b429ae3c3023fce412364016d","schema_version":"1.0","event_id":"sha256:fde312850e30636458f67cb42e40ba4029fcc39b429ae3c3023fce412364016d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:F7L6IUPJDFN5GPJNLUU3UMREHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised word segmentation and lexicon discovery using acoustic word embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aren Jansen, Herman Kamper, Sharon Goldwater","submitted_at":"2016-03-09T11:14:23Z","abstract_excerpt":"In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language acquisition. In these cases, categorical linguistic structure needs to be discovered directly from speech audio. We present a novel unsupervised Bayesian model that segments unlabelled speech and clusters the segments into hypothesized word groupings. The result is a complete unsupervised tokenization of the input speech in terms of discovered word types. In o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02845","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":""},"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":"2026-05-18T01:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrqljntRj5FElrsS54jeZUTTXgH9LDP3QrVreP5V2NjrNT35oiktrdtBdn1uhK87B5A0ON8Xegub8C6RpSn0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:29:57.481181Z"},"content_sha256":"c1cc786249bedbf9e315a790c0c69ca7f47c1a2607173ef51183c262a2f564f2","schema_version":"1.0","event_id":"sha256:c1cc786249bedbf9e315a790c0c69ca7f47c1a2607173ef51183c262a2f564f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7L6IUPJDFN5GPJNLUU3UMREHW/bundle.json","state_url":"https://pith.science/pith/F7L6IUPJDFN5GPJNLUU3UMREHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7L6IUPJDFN5GPJNLUU3UMREHW/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":"2026-06-04T19:29:57Z","links":{"resolver":"https://pith.science/pith/F7L6IUPJDFN5GPJNLUU3UMREHW","bundle":"https://pith.science/pith/F7L6IUPJDFN5GPJNLUU3UMREHW/bundle.json","state":"https://pith.science/pith/F7L6IUPJDFN5GPJNLUU3UMREHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7L6IUPJDFN5GPJNLUU3UMREHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:F7L6IUPJDFN5GPJNLUU3UMREHW","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":"603902fae8bd092db007bf99bdc7023b3d4564ad77a2165ee7826b3342fe0e7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-09T11:14:23Z","title_canon_sha256":"13d9355f5043dce98fd539051528d0dc73bcf3449c65563ae2adc1cc1e488042"},"schema_version":"1.0","source":{"id":"1603.02845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.02845","created_at":"2026-05-18T01:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"1603.02845v1","created_at":"2026-05-18T01:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02845","created_at":"2026-05-18T01:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"F7L6IUPJDFN5","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"F7L6IUPJDFN5GPJN","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"F7L6IUPJ","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:c1cc786249bedbf9e315a790c0c69ca7f47c1a2607173ef51183c262a2f564f2","target":"graph","created_at":"2026-05-18T01:19:19Z","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"},"paper":{"abstract_excerpt":"In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language acquisition. In these cases, categorical linguistic structure needs to be discovered directly from speech audio. We present a novel unsupervised Bayesian model that segments unlabelled speech and clusters the segments into hypothesized word groupings. The result is a complete unsupervised tokenization of the input speech in terms of discovered word types. In o","authors_text":"Aren Jansen, Herman Kamper, Sharon Goldwater","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-09T11:14:23Z","title":"Unsupervised word segmentation and lexicon discovery using acoustic word embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02845","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:fde312850e30636458f67cb42e40ba4029fcc39b429ae3c3023fce412364016d","target":"record","created_at":"2026-05-18T01:19:19Z","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":"603902fae8bd092db007bf99bdc7023b3d4564ad77a2165ee7826b3342fe0e7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-09T11:14:23Z","title_canon_sha256":"13d9355f5043dce98fd539051528d0dc73bcf3449c65563ae2adc1cc1e488042"},"schema_version":"1.0","source":{"id":"1603.02845","kind":"arxiv","version":1}},"canonical_sha256":"2fd7e451e9195bd33d2d5d29ba32243db48af3598f3d957b09651c5ce903c24e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fd7e451e9195bd33d2d5d29ba32243db48af3598f3d957b09651c5ce903c24e","first_computed_at":"2026-05-18T01:19:19.734682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:19.734682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qOMC2lIC3iUiv2xbN8R5bVx45X36rl6NeZQsDruqGHmZHe1QE529U3wOVxUuMHb5El2yy0NjO8YeZw25uGMdBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:19.735210Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.02845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fde312850e30636458f67cb42e40ba4029fcc39b429ae3c3023fce412364016d","sha256:c1cc786249bedbf9e315a790c0c69ca7f47c1a2607173ef51183c262a2f564f2"],"state_sha256":"32bc078a5040a319a8c60f71d4957e895c083d971ba8d2dd118db8a29d140894"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LuGeVGS6DczHJjCazB15kVKmspW6jEnaRXJBm/8gYzrKjvmOzNSUGtcpRoVVhbRz4IyNARdECvuu9JR+zYCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T19:29:57.483163Z","bundle_sha256":"c25578e7fea5db2bfd75104a81b028ee2832c0ae56f646b20c564f76bd502551"}}