{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FCIWUWIEGUK467I2G7QJRJKL7V","short_pith_number":"pith:FCIWUWIE","canonical_record":{"source":{"id":"1810.12566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T08:11:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4a07a53a39a09de56ec80541c342b713703c098e43a34f770bee7c02bc2aa756","abstract_canon_sha256":"471c609a85b4dbbdb3f52f544dbc2b3956bf8361a550c8d4035e5a90b19fa5dd"},"schema_version":"1.0"},"canonical_sha256":"28916a59043515cf7d1a37e098a54bfd7fff314f217d5559061b9f862892aa58","source":{"kind":"arxiv","id":"1810.12566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12566","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12566v1","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12566","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"FCIWUWIEGUK4","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FCIWUWIEGUK467I2","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FCIWUWIE","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FCIWUWIEGUK467I2G7QJRJKL7V","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T08:11:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4a07a53a39a09de56ec80541c342b713703c098e43a34f770bee7c02bc2aa756","abstract_canon_sha256":"471c609a85b4dbbdb3f52f544dbc2b3956bf8361a550c8d4035e5a90b19fa5dd"},"schema_version":"1.0"},"canonical_sha256":"28916a59043515cf7d1a37e098a54bfd7fff314f217d5559061b9f862892aa58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:56.686490Z","signature_b64":"EIqvWluiK9Ge2PJuCpUpuiyqKyaprN0X9HelUQtA5iDdKBVzv1v5PSvBnU0xjljouMq4ArKr14Yr7exERuFvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28916a59043515cf7d1a37e098a54bfd7fff314f217d5559061b9f862892aa58","last_reissued_at":"2026-05-18T00:01:56.685887Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:56.685887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12566","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":"2026-05-18T00:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcK3odpuair/Sls1qtKXQszP2SRymDi7SLgnAYPUznkuxV80rOfHaGteOw/x6b9p0IRFTNgJHQtgkdTySW7tDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:51:09.874851Z"},"content_sha256":"42a5e714b8892f8a4bf0be1db50c4bd390eb3e230ad56285a0b6b627f4868192","schema_version":"1.0","event_id":"sha256:42a5e714b8892f8a4bf0be1db50c4bd390eb3e230ad56285a0b6b627f4868192"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FCIWUWIEGUK467I2G7QJRJKL7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chia-Hao Shen, Hung-yi Lee, Lin-shan Lee, Sung-Feng Huang, Yi-Chen Chen","submitted_at":"2018-10-30T08:11:45Z","abstract_excerpt":"Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds of a small number of exemplar words without hearing a large amount of data. We initiate some preliminary work in this direction in this paper. Audio Word2Vec is used to obtain embeddings of spoken words which carry phonetic information extracted from the signals. An autoencoder is used to generate embeddings of text words based on the articulatory features f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12566","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":"2026-05-18T00:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWo18Ib1VF6up4yqNz9aZ3H1BMq8C2E6bR6WYVdz5BWDKe9wQ9w4lQBYDw4YpkeOlCojWRb4fXzPX4hXCU5rDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:51:09.875327Z"},"content_sha256":"317246e19715704f4e83ab72199696ba779e5b1be222ede0da842650befe87ee","schema_version":"1.0","event_id":"sha256:317246e19715704f4e83ab72199696ba779e5b1be222ede0da842650befe87ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FCIWUWIEGUK467I2G7QJRJKL7V/bundle.json","state_url":"https://pith.science/pith/FCIWUWIEGUK467I2G7QJRJKL7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FCIWUWIEGUK467I2G7QJRJKL7V/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":"2026-05-30T18:51:09Z","links":{"resolver":"https://pith.science/pith/FCIWUWIEGUK467I2G7QJRJKL7V","bundle":"https://pith.science/pith/FCIWUWIEGUK467I2G7QJRJKL7V/bundle.json","state":"https://pith.science/pith/FCIWUWIEGUK467I2G7QJRJKL7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FCIWUWIEGUK467I2G7QJRJKL7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FCIWUWIEGUK467I2G7QJRJKL7V","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":"471c609a85b4dbbdb3f52f544dbc2b3956bf8361a550c8d4035e5a90b19fa5dd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T08:11:45Z","title_canon_sha256":"4a07a53a39a09de56ec80541c342b713703c098e43a34f770bee7c02bc2aa756"},"schema_version":"1.0","source":{"id":"1810.12566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12566","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12566v1","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12566","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"FCIWUWIEGUK4","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FCIWUWIEGUK467I2","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FCIWUWIE","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:317246e19715704f4e83ab72199696ba779e5b1be222ede0da842650befe87ee","target":"graph","created_at":"2026-05-18T00:01:56Z","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":"Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds of a small number of exemplar words without hearing a large amount of data. We initiate some preliminary work in this direction in this paper. Audio Word2Vec is used to obtain embeddings of spoken words which carry phonetic information extracted from the signals. An autoencoder is used to generate embeddings of text words based on the articulatory features f","authors_text":"Chia-Hao Shen, Hung-yi Lee, Lin-shan Lee, Sung-Feng Huang, Yi-Chen Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T08:11:45Z","title":"Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12566","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":"sha256:42a5e714b8892f8a4bf0be1db50c4bd390eb3e230ad56285a0b6b627f4868192","target":"record","created_at":"2026-05-18T00:01:56Z","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":"471c609a85b4dbbdb3f52f544dbc2b3956bf8361a550c8d4035e5a90b19fa5dd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T08:11:45Z","title_canon_sha256":"4a07a53a39a09de56ec80541c342b713703c098e43a34f770bee7c02bc2aa756"},"schema_version":"1.0","source":{"id":"1810.12566","kind":"arxiv","version":1}},"canonical_sha256":"28916a59043515cf7d1a37e098a54bfd7fff314f217d5559061b9f862892aa58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28916a59043515cf7d1a37e098a54bfd7fff314f217d5559061b9f862892aa58","first_computed_at":"2026-05-18T00:01:56.685887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:56.685887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EIqvWluiK9Ge2PJuCpUpuiyqKyaprN0X9HelUQtA5iDdKBVzv1v5PSvBnU0xjljouMq4ArKr14Yr7exERuFvAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:56.686490Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a5e714b8892f8a4bf0be1db50c4bd390eb3e230ad56285a0b6b627f4868192","sha256:317246e19715704f4e83ab72199696ba779e5b1be222ede0da842650befe87ee"],"state_sha256":"7c3f6df6602631921cb65e6ac3571cba840da266138f4ed0c79f2fad163b59f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0r3kKMFU2NmCu8awrnNGrlxnYNnEOeUO55QzJj6dqm1n8t7ql/EtSHdq2LFHbhC9edsTYeSeHpMydf/P/J/IBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:51:09.878533Z","bundle_sha256":"0544f11886e1d020db7c698684ad80313c4080d412a560d2416d589c39dd5e70"}}