{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5G75WK43GHH6V7B7AISCQZFVWE","short_pith_number":"pith:5G75WK43","canonical_record":{"source":{"id":"1802.05092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T13:46:03Z","cross_cats_sorted":[],"title_canon_sha256":"38c737c3addb1351d61391b04fd0527b0f662a1b4e5d796005379da59092e3c5","abstract_canon_sha256":"8ef0ad66a2b65f8ef3b676238799443d173c968b01b6d1256001ca7fa77e8700"},"schema_version":"1.0"},"canonical_sha256":"e9bfdb2b9b31cfeafc3f02242864b5b11f0be116ee59cae770cde961ddaf63c0","source":{"kind":"arxiv","id":"1802.05092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05092","created_at":"2026-05-18T00:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05092v1","created_at":"2026-05-18T00:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05092","created_at":"2026-05-18T00:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"5G75WK43GHH6","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5G75WK43GHH6V7B7","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5G75WK43","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5G75WK43GHH6V7B7AISCQZFVWE","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T13:46:03Z","cross_cats_sorted":[],"title_canon_sha256":"38c737c3addb1351d61391b04fd0527b0f662a1b4e5d796005379da59092e3c5","abstract_canon_sha256":"8ef0ad66a2b65f8ef3b676238799443d173c968b01b6d1256001ca7fa77e8700"},"schema_version":"1.0"},"canonical_sha256":"e9bfdb2b9b31cfeafc3f02242864b5b11f0be116ee59cae770cde961ddaf63c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:20.517704Z","signature_b64":"pHVbPbG8N7i8FpiOQwO2cUUPRgKiDqYtJ11g7ah2nagpwPV/29SkNvT1Y4QtluxDqUXPwVawVlvXkceLlADvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9bfdb2b9b31cfeafc3f02242864b5b11f0be116ee59cae770cde961ddaf63c0","last_reissued_at":"2026-05-18T00:23:20.517004Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:20.517004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05092","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":"2026-05-18T00:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0JeSHKPyaTtZv+KpzU66svU7gQdK/I6mqmBGnsgK4AbOc/chV/0NdCzirp3fnb92ro7Y8iDgUn9dT9JOra2/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:27:01.073626Z"},"content_sha256":"cc87be38f153714384bbd36289119ef19ea481fe3443ffbe118307d72b5f9d69","schema_version":"1.0","event_id":"sha256:cc87be38f153714384bbd36289119ef19ea481fe3443ffbe118307d72b5f9d69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5G75WK43GHH6V7B7AISCQZFVWE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the \"Speaking Rosetta\" JSALT 2017 Workshop","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Black, Danny Merkx, Elin Larsen, Emmanuel Dupoux, Florian Metze, Francesco Ciannella, Graham Neubig, Laurent Besacier, Liming Wang, Lucas Ondel, Mark Hasegawa-Johnson, Markus Mueller, Mingxing Du, Odette Scharenborg, Philip Arthur, Pierre Godard, Rachid Riad, Sebastian Stueker, Shruti Palaskar","submitted_at":"2018-02-14T13:46:03Z","abstract_excerpt":"We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography. We study the replacement of orthographic transcriptions by images and/or translated text in a well-resourced language to help unsupervised discovery from raw speech."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05092","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":"2026-05-18T00:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pyqe44/hhjkBMc5gtgV4kuzkk86SfRB8xZqudwqa2CtS0vawfrB+Kxz8jYt10x3JmBVUksW6EACzTCJ5pdyNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:27:01.073979Z"},"content_sha256":"bfae6aa7dbc756c887911c76ad6e9b1524cb7d724bd4eed729d60c977fb8ef89","schema_version":"1.0","event_id":"sha256:bfae6aa7dbc756c887911c76ad6e9b1524cb7d724bd4eed729d60c977fb8ef89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5G75WK43GHH6V7B7AISCQZFVWE/bundle.json","state_url":"https://pith.science/pith/5G75WK43GHH6V7B7AISCQZFVWE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5G75WK43GHH6V7B7AISCQZFVWE/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":"2026-06-04T20:27:01Z","links":{"resolver":"https://pith.science/pith/5G75WK43GHH6V7B7AISCQZFVWE","bundle":"https://pith.science/pith/5G75WK43GHH6V7B7AISCQZFVWE/bundle.json","state":"https://pith.science/pith/5G75WK43GHH6V7B7AISCQZFVWE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5G75WK43GHH6V7B7AISCQZFVWE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5G75WK43GHH6V7B7AISCQZFVWE","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":"8ef0ad66a2b65f8ef3b676238799443d173c968b01b6d1256001ca7fa77e8700","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T13:46:03Z","title_canon_sha256":"38c737c3addb1351d61391b04fd0527b0f662a1b4e5d796005379da59092e3c5"},"schema_version":"1.0","source":{"id":"1802.05092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05092","created_at":"2026-05-18T00:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05092v1","created_at":"2026-05-18T00:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05092","created_at":"2026-05-18T00:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"5G75WK43GHH6","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5G75WK43GHH6V7B7","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5G75WK43","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:bfae6aa7dbc756c887911c76ad6e9b1524cb7d724bd4eed729d60c977fb8ef89","target":"graph","created_at":"2026-05-18T00:23:20Z","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 summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography. We study the replacement of orthographic transcriptions by images and/or translated text in a well-resourced language to help unsupervised discovery from raw speech.","authors_text":"Alan Black, Danny Merkx, Elin Larsen, Emmanuel Dupoux, Florian Metze, Francesco Ciannella, Graham Neubig, Laurent Besacier, Liming Wang, Lucas Ondel, Mark Hasegawa-Johnson, Markus Mueller, Mingxing Du, Odette Scharenborg, Philip Arthur, Pierre Godard, Rachid Riad, Sebastian Stueker, Shruti Palaskar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T13:46:03Z","title":"Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the \"Speaking Rosetta\" JSALT 2017 Workshop"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05092","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:cc87be38f153714384bbd36289119ef19ea481fe3443ffbe118307d72b5f9d69","target":"record","created_at":"2026-05-18T00:23:20Z","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":"8ef0ad66a2b65f8ef3b676238799443d173c968b01b6d1256001ca7fa77e8700","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T13:46:03Z","title_canon_sha256":"38c737c3addb1351d61391b04fd0527b0f662a1b4e5d796005379da59092e3c5"},"schema_version":"1.0","source":{"id":"1802.05092","kind":"arxiv","version":1}},"canonical_sha256":"e9bfdb2b9b31cfeafc3f02242864b5b11f0be116ee59cae770cde961ddaf63c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9bfdb2b9b31cfeafc3f02242864b5b11f0be116ee59cae770cde961ddaf63c0","first_computed_at":"2026-05-18T00:23:20.517004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:20.517004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pHVbPbG8N7i8FpiOQwO2cUUPRgKiDqYtJ11g7ah2nagpwPV/29SkNvT1Y4QtluxDqUXPwVawVlvXkceLlADvCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:20.517704Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc87be38f153714384bbd36289119ef19ea481fe3443ffbe118307d72b5f9d69","sha256:bfae6aa7dbc756c887911c76ad6e9b1524cb7d724bd4eed729d60c977fb8ef89"],"state_sha256":"c0552bd2b0cdb9ba62248da889dabda7165738ad3f05868120bee1e0fa87e574"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7aGjfbyiZMWGvrSJ9t0dQBc1a9baPQ762IyPf/Mw9THCGTHVcmOsm0KNTgogpT8LV7fAY2tteD6q5IrivouDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:27:01.076100Z","bundle_sha256":"8fe0d4df55110abfd49972a18a4ee353c4bbf530b2083d3c2c95908aba3a6c79"}}