{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CIWNZECSSUDDRNGBEPABF5O6CT","short_pith_number":"pith:CIWNZECS","canonical_record":{"source":{"id":"2110.06744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T14:25:21Z","cross_cats_sorted":[],"title_canon_sha256":"09889cc7cec6327f1f5eca5375ecd3ae731711fb0b7e7350ee0eb30d94d5b58b","abstract_canon_sha256":"71fb94e25407f4b51df63e822500fd638deb8526f17114f2215df2d32267a83f"},"schema_version":"1.0"},"canonical_sha256":"122cdc9052950638b4c123c012f5de14e3ea7738d604e7a67127d4b2588885bc","source":{"kind":"arxiv","id":"2110.06744","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06744","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06744v1","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06744","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"CIWNZECSSUDD","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"CIWNZECSSUDDRNGB","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"CIWNZECS","created_at":"2026-07-05T03:22:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CIWNZECSSUDDRNGBEPABF5O6CT","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T14:25:21Z","cross_cats_sorted":[],"title_canon_sha256":"09889cc7cec6327f1f5eca5375ecd3ae731711fb0b7e7350ee0eb30d94d5b58b","abstract_canon_sha256":"71fb94e25407f4b51df63e822500fd638deb8526f17114f2215df2d32267a83f"},"schema_version":"1.0"},"canonical_sha256":"122cdc9052950638b4c123c012f5de14e3ea7738d604e7a67127d4b2588885bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:29.105393Z","signature_b64":"KVO5AIZsptjQIWoOAlwfR1KzWkxGgM9jtDzbK9JjlAKRoZ+1HtjSJJ37Y1a6GdEmqXT7umDBKFEenR7eZNjDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"122cdc9052950638b4c123c012f5de14e3ea7738d604e7a67127d4b2588885bc","last_reissued_at":"2026-07-05T03:22:29.104979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:29.104979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06744","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":"2026-07-05T03:22:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oCQWNm43Era/iFlmXw8dXzH06gKDZyN9aUS/gpt5sYgE7X8xDmwEeru/Zmyob8IhUrWLoAlPI6gchvKFiSVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:07:33.728861Z"},"content_sha256":"0a5fe22aa19fb76c65e6a7e82ba4b7aa2edc2e4e97d5fb0e32e3cbba4cfd72e7","schema_version":"1.0","event_id":"sha256:0a5fe22aa19fb76c65e6a7e82ba4b7aa2edc2e4e97d5fb0e32e3cbba4cfd72e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CIWNZECSSUDDRNGBEPABF5O6CT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maged S. Al-shaibani, Maraim Masoud, Mustafa Ghaleb, Zaid Alyafeai","submitted_at":"2021-10-13T14:25:21Z","abstract_excerpt":"The NLP pipeline has evolved dramatically in the last few years. The first step in the pipeline is to find suitable annotated datasets to evaluate the tasks we are trying to solve. Unfortunately, most of the published datasets lack metadata annotations that describe their attributes. Not to mention, the absence of a public catalogue that indexes all the publicly available datasets related to specific regions or languages. When we consider low-resource dialectical languages, for example, this issue becomes more prominent. In this paper we create \\textit{Masader}, the largest public catalogue fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06744","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.06744/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:22:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1HG3IyQjW4nmij9dsd+n3aOo2RLe/IxOJmBUNBva9URa+MyzzpKzH5As9j4+IXCC7zXiqGi71BL6oKRk8g66Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:07:33.729177Z"},"content_sha256":"6c37b919b6407694008506611dfb0ef75842863d208379f853b3781b3b0011d4","schema_version":"1.0","event_id":"sha256:6c37b919b6407694008506611dfb0ef75842863d208379f853b3781b3b0011d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIWNZECSSUDDRNGBEPABF5O6CT/bundle.json","state_url":"https://pith.science/pith/CIWNZECSSUDDRNGBEPABF5O6CT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIWNZECSSUDDRNGBEPABF5O6CT/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":"2026-08-14T13:07:33Z","links":{"resolver":"https://pith.science/pith/CIWNZECSSUDDRNGBEPABF5O6CT","bundle":"https://pith.science/pith/CIWNZECSSUDDRNGBEPABF5O6CT/bundle.json","state":"https://pith.science/pith/CIWNZECSSUDDRNGBEPABF5O6CT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIWNZECSSUDDRNGBEPABF5O6CT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CIWNZECSSUDDRNGBEPABF5O6CT","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":"71fb94e25407f4b51df63e822500fd638deb8526f17114f2215df2d32267a83f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T14:25:21Z","title_canon_sha256":"09889cc7cec6327f1f5eca5375ecd3ae731711fb0b7e7350ee0eb30d94d5b58b"},"schema_version":"1.0","source":{"id":"2110.06744","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06744","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06744v1","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06744","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"CIWNZECSSUDD","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"CIWNZECSSUDDRNGB","created_at":"2026-07-05T03:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"CIWNZECS","created_at":"2026-07-05T03:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:6c37b919b6407694008506611dfb0ef75842863d208379f853b3781b3b0011d4","target":"graph","created_at":"2026-07-05T03:22:29Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.06744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The NLP pipeline has evolved dramatically in the last few years. The first step in the pipeline is to find suitable annotated datasets to evaluate the tasks we are trying to solve. Unfortunately, most of the published datasets lack metadata annotations that describe their attributes. Not to mention, the absence of a public catalogue that indexes all the publicly available datasets related to specific regions or languages. When we consider low-resource dialectical languages, for example, this issue becomes more prominent. In this paper we create \\textit{Masader}, the largest public catalogue fo","authors_text":"Maged S. Al-shaibani, Maraim Masoud, Mustafa Ghaleb, Zaid Alyafeai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T14:25:21Z","title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06744","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":"sha256:0a5fe22aa19fb76c65e6a7e82ba4b7aa2edc2e4e97d5fb0e32e3cbba4cfd72e7","target":"record","created_at":"2026-07-05T03:22:29Z","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":"71fb94e25407f4b51df63e822500fd638deb8526f17114f2215df2d32267a83f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T14:25:21Z","title_canon_sha256":"09889cc7cec6327f1f5eca5375ecd3ae731711fb0b7e7350ee0eb30d94d5b58b"},"schema_version":"1.0","source":{"id":"2110.06744","kind":"arxiv","version":1}},"canonical_sha256":"122cdc9052950638b4c123c012f5de14e3ea7738d604e7a67127d4b2588885bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"122cdc9052950638b4c123c012f5de14e3ea7738d604e7a67127d4b2588885bc","first_computed_at":"2026-07-05T03:22:29.104979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:29.104979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KVO5AIZsptjQIWoOAlwfR1KzWkxGgM9jtDzbK9JjlAKRoZ+1HtjSJJ37Y1a6GdEmqXT7umDBKFEenR7eZNjDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:29.105393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06744","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a5fe22aa19fb76c65e6a7e82ba4b7aa2edc2e4e97d5fb0e32e3cbba4cfd72e7","sha256:6c37b919b6407694008506611dfb0ef75842863d208379f853b3781b3b0011d4"],"state_sha256":"4231cb9f825af54f4f61c8bd78df852bd4d5c057aa597ff338342a47610e06d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TI+ZKuWfgJ/jgHKQUoXTUG9NS+5DOit1KzZ9/2WJZ30/XSXK2A1KtwDCbylVjl7dPdOiipHCEo4xQ9DJgmR3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:07:33.732668Z","bundle_sha256":"53a6e6ad36b604627ef78ae0748454bf3f8817cde33dfd69fdca941471a2ad9e"}}