{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3SPBJZ3ZPYRGJRVKM7LJ6SL2PL","short_pith_number":"pith:3SPBJZ3Z","canonical_record":{"source":{"id":"1701.00851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-03T22:26:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be3b020311799975307cb7a8a3bd23d69b82d38db61050059dd12a0dc05b5d23","abstract_canon_sha256":"99b1c42e66bf9ecd85b161369c6d8f51478d161248eac7f68eacf1b1d0ca2198"},"schema_version":"1.0"},"canonical_sha256":"dc9e14e7797e2264c6aa67d69f497a7ac594d9b09054ee222f14e0fd07a98f9c","source":{"kind":"arxiv","id":"1701.00851","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00851","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00851v1","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00851","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"3SPBJZ3ZPYRG","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3SPBJZ3ZPYRGJRVK","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3SPBJZ3Z","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3SPBJZ3ZPYRGJRVKM7LJ6SL2PL","target":"record","payload":{"canonical_record":{"source":{"id":"1701.00851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-03T22:26:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be3b020311799975307cb7a8a3bd23d69b82d38db61050059dd12a0dc05b5d23","abstract_canon_sha256":"99b1c42e66bf9ecd85b161369c6d8f51478d161248eac7f68eacf1b1d0ca2198"},"schema_version":"1.0"},"canonical_sha256":"dc9e14e7797e2264c6aa67d69f497a7ac594d9b09054ee222f14e0fd07a98f9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:22.053610Z","signature_b64":"80a+JGXh0n5XF6S9DBR3mQGI+r8wELpxervbsFcnR2gQ0AkJNTnU8mn4/wMp5TazwykfXoFyrnywGf/HEvydCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc9e14e7797e2264c6aa67d69f497a7ac594d9b09054ee222f14e0fd07a98f9c","last_reissued_at":"2026-05-18T00:53:22.053145Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:22.053145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.00851","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":"2026-05-18T00:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruu6g1HgLxVXSakFprcnYlnRNgDkH6LhRSFKFyBl5CHjqcplhh4/i7CtMCLPdU2yI+pWLKsyCRBlVcDYqZ7aBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:27:33.865853Z"},"content_sha256":"260296b308ce17745c436b47c2b80efe24112022c03b78e66bd5828d1607fcb9","schema_version":"1.0","event_id":"sha256:260296b308ce17745c436b47c2b80efe24112022c03b78e66bd5828d1607fcb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3SPBJZ3ZPYRGJRVKM7LJ6SL2PL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised neural and Bayesian models for zero-resource speech processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Herman Kamper","submitted_at":"2017-01-03T22:26:10Z","abstract_excerpt":"In settings where only unlabelled speech data is available, zero-resource speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. There are two central problems in zero-resource speech processing: (i) finding frame-level feature representations which make it easier to discriminate between linguistic units (phones or words), and (ii) segmenting and clustering unlabelled speech into meaningful units. In this thesis, we argue that a combination of top-down and bottom-up modelling is advantageous in tackling these two problems.\n  To a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00851","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":"2026-05-18T00:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjaDYhyy8bbBQX+QF8S2tqC+dMaN4Be9mUyPvMSxK2+CpC18veVSrF3Dl1+atCUHT7aUilh3wti8NcQWFvyUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:27:33.866479Z"},"content_sha256":"e8fc6e81a2595fe1afa7c5a7b504f6d5b58b98ad2941acb37dae484410356d06","schema_version":"1.0","event_id":"sha256:e8fc6e81a2595fe1afa7c5a7b504f6d5b58b98ad2941acb37dae484410356d06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL/bundle.json","state_url":"https://pith.science/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL/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":"2026-06-06T21:27:33Z","links":{"resolver":"https://pith.science/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL","bundle":"https://pith.science/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL/bundle.json","state":"https://pith.science/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3SPBJZ3ZPYRGJRVKM7LJ6SL2PL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3SPBJZ3ZPYRGJRVKM7LJ6SL2PL","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":"99b1c42e66bf9ecd85b161369c6d8f51478d161248eac7f68eacf1b1d0ca2198","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-03T22:26:10Z","title_canon_sha256":"be3b020311799975307cb7a8a3bd23d69b82d38db61050059dd12a0dc05b5d23"},"schema_version":"1.0","source":{"id":"1701.00851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00851","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00851v1","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00851","created_at":"2026-05-18T00:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"3SPBJZ3ZPYRG","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3SPBJZ3ZPYRGJRVK","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3SPBJZ3Z","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:e8fc6e81a2595fe1afa7c5a7b504f6d5b58b98ad2941acb37dae484410356d06","target":"graph","created_at":"2026-05-18T00:53:22Z","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, zero-resource speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. There are two central problems in zero-resource speech processing: (i) finding frame-level feature representations which make it easier to discriminate between linguistic units (phones or words), and (ii) segmenting and clustering unlabelled speech into meaningful units. In this thesis, we argue that a combination of top-down and bottom-up modelling is advantageous in tackling these two problems.\n  To a","authors_text":"Herman Kamper","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-03T22:26:10Z","title":"Unsupervised neural and Bayesian models for zero-resource speech processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00851","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":"sha256:260296b308ce17745c436b47c2b80efe24112022c03b78e66bd5828d1607fcb9","target":"record","created_at":"2026-05-18T00:53:22Z","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":"99b1c42e66bf9ecd85b161369c6d8f51478d161248eac7f68eacf1b1d0ca2198","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-03T22:26:10Z","title_canon_sha256":"be3b020311799975307cb7a8a3bd23d69b82d38db61050059dd12a0dc05b5d23"},"schema_version":"1.0","source":{"id":"1701.00851","kind":"arxiv","version":1}},"canonical_sha256":"dc9e14e7797e2264c6aa67d69f497a7ac594d9b09054ee222f14e0fd07a98f9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc9e14e7797e2264c6aa67d69f497a7ac594d9b09054ee222f14e0fd07a98f9c","first_computed_at":"2026-05-18T00:53:22.053145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:22.053145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"80a+JGXh0n5XF6S9DBR3mQGI+r8wELpxervbsFcnR2gQ0AkJNTnU8mn4/wMp5TazwykfXoFyrnywGf/HEvydCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:22.053610Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.00851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:260296b308ce17745c436b47c2b80efe24112022c03b78e66bd5828d1607fcb9","sha256:e8fc6e81a2595fe1afa7c5a7b504f6d5b58b98ad2941acb37dae484410356d06"],"state_sha256":"f0384fe69475d527fc0dd879f5f30488feac0d1948ebe099d75593cf9d2ef7f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MR7ASppvB5KydADbmP0EsAVaTQiSW/13SOWbLJYlCL7imTyhj4q+XDAPuZXV+5EbqiSjFoaWakLiGgrc8WBPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T21:27:33.869754Z","bundle_sha256":"98c4069996b50dd4b57dfafba22e3646e47944eceedcb1b5e04cefd42b34c74c"}}