{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:BHTHPTNRRFPFAUSO3BUKH2OVHI","short_pith_number":"pith:BHTHPTNR","canonical_record":{"source":{"id":"1509.06928","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-23T11:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"98ab0f92e576716f1955e6c8e00d9e94fadbf8639f0b958840558b13cc615795","abstract_canon_sha256":"3d2faf99402484114121c01ec50845f99859f33417a41ed276b6c71b74077100"},"schema_version":"1.0"},"canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","source":{"kind":"arxiv","id":"1509.06928","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.06928","created_at":"2026-05-18T01:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"1509.06928v2","created_at":"2026-05-18T01:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06928","created_at":"2026-05-18T01:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"BHTHPTNRRFPF","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BHTHPTNRRFPFAUSO","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BHTHPTNR","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:BHTHPTNRRFPFAUSO3BUKH2OVHI","target":"record","payload":{"canonical_record":{"source":{"id":"1509.06928","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-23T11:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"98ab0f92e576716f1955e6c8e00d9e94fadbf8639f0b958840558b13cc615795","abstract_canon_sha256":"3d2faf99402484114121c01ec50845f99859f33417a41ed276b6c71b74077100"},"schema_version":"1.0"},"canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:29.699295Z","signature_b64":"rr6i+Q/px9wFzPxlPrWam4mfGOXnk22FF9cV6HEG35fhCrw5lEl+aAyH7zTYy2IRTGr+a3Yi24HGl0KdfCbEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","last_reissued_at":"2026-05-18T01:09:29.698923Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:29.698923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.06928","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C3DoOO8gvpX8PpnCub4pjjZ+wL9SJptJuh6FP3UMRVHs7pdKeAQNxKnjeZtGku+N55FBhuMv+jFli/nOniU4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:45:25.480831Z"},"content_sha256":"513073c9131553a364b046a5e76d54fc386d8eb7927f1431cda186eef0128fe0","schema_version":"1.0","event_id":"sha256:513073c9131553a364b046a5e76d54fc386d8eb7927f1431cda186eef0128fe0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:BHTHPTNRRFPFAUSO3BUKH2OVHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Dialect Detection in Arabic Broadcast Speech","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Ali, James Glass, Najim Dehak, Patrick Cardinal, Peter Bell, Sameer Khurana, Sree Harsha Yella, Steve Renals","submitted_at":"2015-09-23T11:41:10Z","abstract_excerpt":"We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06928","kind":"arxiv","version":2},"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":"2026-05-18T01:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVjkoHgGgCoIPDJdG6izSraFfPOeJ4y8tYwm9x8nkvfaEjxj1IFme4QTbE5tum+lf3+GA7RPF+F5HEhxIzW9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:45:25.481507Z"},"content_sha256":"83449be5a4558eccd2aa246daf5f5cb7f18844438edd2f473333de206f1c3a10","schema_version":"1.0","event_id":"sha256:83449be5a4558eccd2aa246daf5f5cb7f18844438edd2f473333de206f1c3a10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/bundle.json","state_url":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/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":"2026-05-27T21:45:25Z","links":{"resolver":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI","bundle":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/bundle.json","state":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:BHTHPTNRRFPFAUSO3BUKH2OVHI","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":"3d2faf99402484114121c01ec50845f99859f33417a41ed276b6c71b74077100","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-23T11:41:10Z","title_canon_sha256":"98ab0f92e576716f1955e6c8e00d9e94fadbf8639f0b958840558b13cc615795"},"schema_version":"1.0","source":{"id":"1509.06928","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.06928","created_at":"2026-05-18T01:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"1509.06928v2","created_at":"2026-05-18T01:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06928","created_at":"2026-05-18T01:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"BHTHPTNRRFPF","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BHTHPTNRRFPFAUSO","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BHTHPTNR","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:83449be5a4558eccd2aa246daf5f5cb7f18844438edd2f473333de206f1c3a10","target":"graph","created_at":"2026-05-18T01:09:29Z","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 investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of ","authors_text":"Ahmed Ali, James Glass, Najim Dehak, Patrick Cardinal, Peter Bell, Sameer Khurana, Sree Harsha Yella, Steve Renals","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-23T11:41:10Z","title":"Automatic Dialect Detection in Arabic Broadcast Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06928","kind":"arxiv","version":2},"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":"sha256:513073c9131553a364b046a5e76d54fc386d8eb7927f1431cda186eef0128fe0","target":"record","created_at":"2026-05-18T01:09:29Z","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":"3d2faf99402484114121c01ec50845f99859f33417a41ed276b6c71b74077100","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-23T11:41:10Z","title_canon_sha256":"98ab0f92e576716f1955e6c8e00d9e94fadbf8639f0b958840558b13cc615795"},"schema_version":"1.0","source":{"id":"1509.06928","kind":"arxiv","version":2}},"canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","first_computed_at":"2026-05-18T01:09:29.698923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:29.698923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rr6i+Q/px9wFzPxlPrWam4mfGOXnk22FF9cV6HEG35fhCrw5lEl+aAyH7zTYy2IRTGr+a3Yi24HGl0KdfCbEDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:29.699295Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.06928","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:513073c9131553a364b046a5e76d54fc386d8eb7927f1431cda186eef0128fe0","sha256:83449be5a4558eccd2aa246daf5f5cb7f18844438edd2f473333de206f1c3a10"],"state_sha256":"cbd1493938a8ceeecec54632d6d5c5c6337cc2a662277af24f171ddb94727af7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z65+A7zldsi92cuZv6SWD01CxO01xn4ZwQ0l6+xjQPe9IUQs2NY4pHbgqudKd9L2t1G+i/nrRhMrQoxC+7fcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:45:25.484707Z","bundle_sha256":"c091c9dc1cca2ab5f35c34f4fa6afc4f32331e494a86f0d95c54557015f8ef02"}}