{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UKV577Q3YR66E7JJGFTTP2QDJX","short_pith_number":"pith:UKV577Q3","canonical_record":{"source":{"id":"1806.06734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T14:35:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09c310e6cf1fefc7782ed6fee577ad976dbc65d50410b1181f6ea324cd020c57","abstract_canon_sha256":"0f977cf72fe9ae2833b54c0f5ec44177f5fbfffd6ddb0080c7db80af82f10086"},"schema_version":"1.0"},"canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","source":{"kind":"arxiv","id":"1806.06734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06734","created_at":"2026-05-18T00:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06734v1","created_at":"2026-05-18T00:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06734","created_at":"2026-05-18T00:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"UKV577Q3YR66","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UKV577Q3YR66E7JJ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UKV577Q3","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UKV577Q3YR66E7JJGFTTP2QDJX","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T14:35:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09c310e6cf1fefc7782ed6fee577ad976dbc65d50410b1181f6ea324cd020c57","abstract_canon_sha256":"0f977cf72fe9ae2833b54c0f5ec44177f5fbfffd6ddb0080c7db80af82f10086"},"schema_version":"1.0"},"canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:59.284212Z","signature_b64":"pQZTIvNopdexA0aq4vkuGxOjYcJiZZmabmT7MyE9tNMnDP+C7E1FlFNk5eNr1Oq4H923OzAMsXgBLAtZZM8CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","last_reissued_at":"2026-05-18T00:12:59.283554Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:59.283554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06734","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":"2026-05-18T00:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obqXJs2hv1ylZd4fJ4xtSzpTd8M7U7SsFxTSOaTeIfkvXxD8L2DaotTy0Qh2dwir88japVGOos+VL9YNYFBeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:52:47.909645Z"},"content_sha256":"039336290d3a70c325fa5aec4b852cd1c1cc4d8e7a96b61da05847c442e08c1a","schema_version":"1.0","event_id":"sha256:039336290d3a70c325fa5aec4b852cd1c1cc4d8e7a96b61da05847c442e08c1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UKV577Q3YR66E7JJGFTTP2QDJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Word Segmentation from Speech with Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Aline Villavicencio, Fran\\c{c}ois Yvon, Laurent Besacier, Lucas Ondel, Marcely Zanon-Boito, Pierre Godard","submitted_at":"2018-06-18T14:35:14Z","abstract_excerpt":"We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06734","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":"2026-05-18T00:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGe+9ko+5/fKmeQAYT44c+cHVmfg3OJtFKtvcESdl0k2xgdtWx/zcQa+OcgBwTrOoOLs9XUDu8uiFklmVC8aBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:52:47.910012Z"},"content_sha256":"b485281ed92aeba874bc3ef53543c5c00e57aac5bc60b853b6c5446c5d15ac34","schema_version":"1.0","event_id":"sha256:b485281ed92aeba874bc3ef53543c5c00e57aac5bc60b853b6c5446c5d15ac34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/bundle.json","state_url":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKV577Q3YR66E7JJGFTTP2QDJX/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":"2026-05-25T22:52:47Z","links":{"resolver":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX","bundle":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/bundle.json","state":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKV577Q3YR66E7JJGFTTP2QDJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UKV577Q3YR66E7JJGFTTP2QDJX","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":"0f977cf72fe9ae2833b54c0f5ec44177f5fbfffd6ddb0080c7db80af82f10086","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T14:35:14Z","title_canon_sha256":"09c310e6cf1fefc7782ed6fee577ad976dbc65d50410b1181f6ea324cd020c57"},"schema_version":"1.0","source":{"id":"1806.06734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06734","created_at":"2026-05-18T00:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06734v1","created_at":"2026-05-18T00:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06734","created_at":"2026-05-18T00:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"UKV577Q3YR66","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UKV577Q3YR66E7JJ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UKV577Q3","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:b485281ed92aeba874bc3ef53543c5c00e57aac5bc60b853b6c5446c5d15ac34","target":"graph","created_at":"2026-05-18T00:12:59Z","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":"We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illus","authors_text":"Alexandre Berard, Aline Villavicencio, Fran\\c{c}ois Yvon, Laurent Besacier, Lucas Ondel, Marcely Zanon-Boito, Pierre Godard","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T14:35:14Z","title":"Unsupervised Word Segmentation from Speech with Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06734","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":"sha256:039336290d3a70c325fa5aec4b852cd1c1cc4d8e7a96b61da05847c442e08c1a","target":"record","created_at":"2026-05-18T00:12:59Z","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":"0f977cf72fe9ae2833b54c0f5ec44177f5fbfffd6ddb0080c7db80af82f10086","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T14:35:14Z","title_canon_sha256":"09c310e6cf1fefc7782ed6fee577ad976dbc65d50410b1181f6ea324cd020c57"},"schema_version":"1.0","source":{"id":"1806.06734","kind":"arxiv","version":1}},"canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","first_computed_at":"2026-05-18T00:12:59.283554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:59.283554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQZTIvNopdexA0aq4vkuGxOjYcJiZZmabmT7MyE9tNMnDP+C7E1FlFNk5eNr1Oq4H923OzAMsXgBLAtZZM8CAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:59.284212Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039336290d3a70c325fa5aec4b852cd1c1cc4d8e7a96b61da05847c442e08c1a","sha256:b485281ed92aeba874bc3ef53543c5c00e57aac5bc60b853b6c5446c5d15ac34"],"state_sha256":"5b727b3983675fe4ccf8519ad13c66ea53e944f57b3c0a701176427b0e388b5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAGdfB95kz4rL2xZkoqZG/GEN/ne4DjAcHBs4VDKhmRgM/dksJDZCcVByzO3UieGZY1ReeIYauFtlh3AHi3SBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:52:47.912773Z","bundle_sha256":"f1f572c78f02b16f6939474fc6d3cddd76dc8ef5e8070cc4d7fd9200060dc5ce"}}