{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MCCUZ6STK7LIY2ZLS6WHTGH7WE","short_pith_number":"pith:MCCUZ6ST","canonical_record":{"source":{"id":"1709.00387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-28T14:20:02Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"34a4350dffcec1a570d3622d440ff90191aeec00dadcaf516287394ac9f36a6f","abstract_canon_sha256":"6c7083e9ab9fa31863d4ce17522c1497a4561df55718a30bc7a96e5f63be38a5"},"schema_version":"1.0"},"canonical_sha256":"60854cfa5357d68c6b2b97ac7998ffb1280f9a84e491a7247d98a39ba42d29ab","source":{"kind":"arxiv","id":"1709.00387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00387","created_at":"2026-05-18T00:36:10Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00387v1","created_at":"2026-05-18T00:36:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00387","created_at":"2026-05-18T00:36:10Z"},{"alias_kind":"pith_short_12","alias_value":"MCCUZ6STK7LI","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MCCUZ6STK7LIY2ZL","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MCCUZ6ST","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MCCUZ6STK7LIY2ZLS6WHTGH7WE","target":"record","payload":{"canonical_record":{"source":{"id":"1709.00387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-28T14:20:02Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"34a4350dffcec1a570d3622d440ff90191aeec00dadcaf516287394ac9f36a6f","abstract_canon_sha256":"6c7083e9ab9fa31863d4ce17522c1497a4561df55718a30bc7a96e5f63be38a5"},"schema_version":"1.0"},"canonical_sha256":"60854cfa5357d68c6b2b97ac7998ffb1280f9a84e491a7247d98a39ba42d29ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:10.493048Z","signature_b64":"Oplk7wv1L1CFtynUODU1Xxf3gXK/7MLrH8+eFiz7NaGPl8D903nUCZSU7RcFwyCZS76UcKf7dFDn3rBJuavNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60854cfa5357d68c6b2b97ac7998ffb1280f9a84e491a7247d98a39ba42d29ab","last_reissued_at":"2026-05-18T00:36:10.492386Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:10.492386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.00387","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":"2026-05-18T00:36:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ySErifGedlu15T9gmIDTUenhHQcIhD5l+yjfp6Y8opx7h0dBlxhUGT/FiMTIpnbCLKns8MZDfDLWPUOpnIE9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:53:25.284930Z"},"content_sha256":"56899294ca671db601a506cf13ad9162af8406f058498a2b48ba586e4d44f8f7","schema_version":"1.0","event_id":"sha256:56899294ca671db601a506cf13ad9162af8406f058498a2b48ba586e4d44f8f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MCCUZ6STK7LIY2ZLS6WHTGH7WE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Ahmed Ali, James Glass, Suwon Shon","submitted_at":"2017-08-28T14:20:02Z","abstract_excerpt":"In order to successfully annotate the Arabic speech con- tent found in open-domain media broadcasts, it is essential to be able to process a diverse set of Arabic dialects. For the 2017 Multi-Genre Broadcast challenge (MGB-3) there were two possible tasks: Arabic speech recognition, and Arabic Dialect Identification (ADI). In this paper, we describe our efforts to create an ADI system for the MGB-3 challenge, with the goal of distinguishing amongst four major Arabic dialects, as well as Modern Standard Arabic. Our research fo- cused on dialect variability and domain mismatches between the trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00387","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":"2026-05-18T00:36:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtqcWdtTGypVglg8Kkjqgw6Utp5AGcHcixZfPthI5cX5Xio2uhMBNpqTMLVsjZXNp3beXYl8nhlXQIX2BylbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:53:25.285370Z"},"content_sha256":"21796e6e69cc6491ac97b8514f355ffa9b574ec483b70ec93bba336ff3176ccd","schema_version":"1.0","event_id":"sha256:21796e6e69cc6491ac97b8514f355ffa9b574ec483b70ec93bba336ff3176ccd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE/bundle.json","state_url":"https://pith.science/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE/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":"2026-05-27T21:53:25Z","links":{"resolver":"https://pith.science/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE","bundle":"https://pith.science/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE/bundle.json","state":"https://pith.science/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCCUZ6STK7LIY2ZLS6WHTGH7WE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MCCUZ6STK7LIY2ZLS6WHTGH7WE","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":"6c7083e9ab9fa31863d4ce17522c1497a4561df55718a30bc7a96e5f63be38a5","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-28T14:20:02Z","title_canon_sha256":"34a4350dffcec1a570d3622d440ff90191aeec00dadcaf516287394ac9f36a6f"},"schema_version":"1.0","source":{"id":"1709.00387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00387","created_at":"2026-05-18T00:36:10Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00387v1","created_at":"2026-05-18T00:36:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00387","created_at":"2026-05-18T00:36:10Z"},{"alias_kind":"pith_short_12","alias_value":"MCCUZ6STK7LI","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MCCUZ6STK7LIY2ZL","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MCCUZ6ST","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:21796e6e69cc6491ac97b8514f355ffa9b574ec483b70ec93bba336ff3176ccd","target":"graph","created_at":"2026-05-18T00:36:10Z","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 order to successfully annotate the Arabic speech con- tent found in open-domain media broadcasts, it is essential to be able to process a diverse set of Arabic dialects. For the 2017 Multi-Genre Broadcast challenge (MGB-3) there were two possible tasks: Arabic speech recognition, and Arabic Dialect Identification (ADI). In this paper, we describe our efforts to create an ADI system for the MGB-3 challenge, with the goal of distinguishing amongst four major Arabic dialects, as well as Modern Standard Arabic. Our research fo- cused on dialect variability and domain mismatches between the trai","authors_text":"Ahmed Ali, James Glass, Suwon Shon","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-28T14:20:02Z","title":"MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00387","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":"sha256:56899294ca671db601a506cf13ad9162af8406f058498a2b48ba586e4d44f8f7","target":"record","created_at":"2026-05-18T00:36:10Z","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":"6c7083e9ab9fa31863d4ce17522c1497a4561df55718a30bc7a96e5f63be38a5","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-28T14:20:02Z","title_canon_sha256":"34a4350dffcec1a570d3622d440ff90191aeec00dadcaf516287394ac9f36a6f"},"schema_version":"1.0","source":{"id":"1709.00387","kind":"arxiv","version":1}},"canonical_sha256":"60854cfa5357d68c6b2b97ac7998ffb1280f9a84e491a7247d98a39ba42d29ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60854cfa5357d68c6b2b97ac7998ffb1280f9a84e491a7247d98a39ba42d29ab","first_computed_at":"2026-05-18T00:36:10.492386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:10.492386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oplk7wv1L1CFtynUODU1Xxf3gXK/7MLrH8+eFiz7NaGPl8D903nUCZSU7RcFwyCZS76UcKf7dFDn3rBJuavNCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:10.493048Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56899294ca671db601a506cf13ad9162af8406f058498a2b48ba586e4d44f8f7","sha256:21796e6e69cc6491ac97b8514f355ffa9b574ec483b70ec93bba336ff3176ccd"],"state_sha256":"130942d8ef5b70b810d9fb18011d983a2cafc38abfd8612970bc195e35e2cd95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uKvIUI/9PbZ40s1jD4ksuZXXAAtynsvtQtKc7498xOYQjWYbhjTvAKrGQkvU5nZoU0IlFjaWbd9VLYL0mRNQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:53:25.287871Z","bundle_sha256":"76a17b937d5e8a664cb5c02da59e0797a904ecaff5af681d486b4621e4b576e6"}}