{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CTSXQA4SN2WGG7FSSV4XOQQYCY","short_pith_number":"pith:CTSXQA4S","canonical_record":{"source":{"id":"2111.02362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-03T17:26:52Z","cross_cats_sorted":[],"title_canon_sha256":"dccf532a136003c26ba5fce50593d6028d2bc99c4bf0c5c8d7d17fed42fd8ad1","abstract_canon_sha256":"2f85bfe71a1e1b5dca1220a518a9c330da92ca292a2038c22ece85fe9c50ba86"},"schema_version":"1.0"},"canonical_sha256":"14e57803926eac637cb2957977421816048f1d334a1b89538bf285546fcb906d","source":{"kind":"arxiv","id":"2111.02362","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02362","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02362v1","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02362","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"CTSXQA4SN2WG","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"CTSXQA4SN2WGG7FS","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"CTSXQA4S","created_at":"2026-07-05T03:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CTSXQA4SN2WGG7FSSV4XOQQYCY","target":"record","payload":{"canonical_record":{"source":{"id":"2111.02362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-03T17:26:52Z","cross_cats_sorted":[],"title_canon_sha256":"dccf532a136003c26ba5fce50593d6028d2bc99c4bf0c5c8d7d17fed42fd8ad1","abstract_canon_sha256":"2f85bfe71a1e1b5dca1220a518a9c330da92ca292a2038c22ece85fe9c50ba86"},"schema_version":"1.0"},"canonical_sha256":"14e57803926eac637cb2957977421816048f1d334a1b89538bf285546fcb906d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:49.923657Z","signature_b64":"eEWe1UyjS3wAs/kOkrWntm1A8gF+uD82a0WyCbl1uUjEi3HFyefEJ+Tz5kYvLjlSRNI+friVCQAGF9cVjfsqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14e57803926eac637cb2957977421816048f1d334a1b89538bf285546fcb906d","last_reissued_at":"2026-07-05T03:28:49.923091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:49.923091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.02362","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":"2026-07-05T03:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jzzmKpNnn3ZM2Gns04BeQzJSvbMmVIWX3XvfrpG1P+GtHUYX07HaP74YJnqkMflXfHFmUit6Zboi7/B1ChR1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:18:06.750633Z"},"content_sha256":"9649a2e42024500a8aa4dfa26eb1b56cf9f90d636e22b58c661a8e1b1e38143f","schema_version":"1.0","event_id":"sha256:9649a2e42024500a8aa4dfa26eb1b56cf9f90d636e22b58c661a8e1b1e38143f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CTSXQA4SN2WGG7FSSV4XOQQYCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HmBlogs: A big general Persian corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hamzeh Motahari Khansari, Mehrnoush Shamsfard","submitted_at":"2021-11-03T17:26:52Z","abstract_excerpt":"This paper introduces the hmBlogs corpus for Persian, as a low resource language. This corpus has been prepared based on a collection of nearly 20 million blog posts over a period of about 15 years from a space of Persian blogs and includes more than 6.8 billion tokens. It can be claimed that this corpus is currently the largest Persian corpus that has been prepared independently for the Persian language. This corpus is presented in both raw and preprocessed forms, and based on the preprocessed corpus some word embedding models are produced. By the provided models, the hmBlogs is compared with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02362","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/2111.02362/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":"2026-07-05T03:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2jpMhnMixJ8g+vXbiKSLJJ+77/rfMR9qjk05+Q2U9oeu7zEP13dMgIhiU4xTvsnyfeDfHDE0rG9DbUG0HGnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:18:06.750955Z"},"content_sha256":"604da57167f37e24c7901346de089aef9878380666c81ab39d013679cd9886f9","schema_version":"1.0","event_id":"sha256:604da57167f37e24c7901346de089aef9878380666c81ab39d013679cd9886f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY/bundle.json","state_url":"https://pith.science/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY/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":"2026-08-18T17:18:06Z","links":{"resolver":"https://pith.science/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY","bundle":"https://pith.science/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY/bundle.json","state":"https://pith.science/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTSXQA4SN2WGG7FSSV4XOQQYCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CTSXQA4SN2WGG7FSSV4XOQQYCY","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":"2f85bfe71a1e1b5dca1220a518a9c330da92ca292a2038c22ece85fe9c50ba86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-03T17:26:52Z","title_canon_sha256":"dccf532a136003c26ba5fce50593d6028d2bc99c4bf0c5c8d7d17fed42fd8ad1"},"schema_version":"1.0","source":{"id":"2111.02362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02362","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02362v1","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02362","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"CTSXQA4SN2WG","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"CTSXQA4SN2WGG7FS","created_at":"2026-07-05T03:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"CTSXQA4S","created_at":"2026-07-05T03:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:604da57167f37e24c7901346de089aef9878380666c81ab39d013679cd9886f9","target":"graph","created_at":"2026-07-05T03:28:49Z","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/2111.02362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces the hmBlogs corpus for Persian, as a low resource language. This corpus has been prepared based on a collection of nearly 20 million blog posts over a period of about 15 years from a space of Persian blogs and includes more than 6.8 billion tokens. It can be claimed that this corpus is currently the largest Persian corpus that has been prepared independently for the Persian language. This corpus is presented in both raw and preprocessed forms, and based on the preprocessed corpus some word embedding models are produced. By the provided models, the hmBlogs is compared with","authors_text":"Hamzeh Motahari Khansari, Mehrnoush Shamsfard","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-03T17:26:52Z","title":"HmBlogs: A big general Persian corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02362","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":"sha256:9649a2e42024500a8aa4dfa26eb1b56cf9f90d636e22b58c661a8e1b1e38143f","target":"record","created_at":"2026-07-05T03:28:49Z","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":"2f85bfe71a1e1b5dca1220a518a9c330da92ca292a2038c22ece85fe9c50ba86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-03T17:26:52Z","title_canon_sha256":"dccf532a136003c26ba5fce50593d6028d2bc99c4bf0c5c8d7d17fed42fd8ad1"},"schema_version":"1.0","source":{"id":"2111.02362","kind":"arxiv","version":1}},"canonical_sha256":"14e57803926eac637cb2957977421816048f1d334a1b89538bf285546fcb906d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14e57803926eac637cb2957977421816048f1d334a1b89538bf285546fcb906d","first_computed_at":"2026-07-05T03:28:49.923091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:28:49.923091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eEWe1UyjS3wAs/kOkrWntm1A8gF+uD82a0WyCbl1uUjEi3HFyefEJ+Tz5kYvLjlSRNI+friVCQAGF9cVjfsqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:28:49.923657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.02362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9649a2e42024500a8aa4dfa26eb1b56cf9f90d636e22b58c661a8e1b1e38143f","sha256:604da57167f37e24c7901346de089aef9878380666c81ab39d013679cd9886f9"],"state_sha256":"6780528d4ebf04403080ba3794063bdd3d0931064b9657ebd24f94ef54cd4b1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFjl9O+nzWM1b1lv3ehVd34OBsQoz109anQ9p22cjdcKyuLfX/mNfmIBjgqAtJNImD1BM60/aayQYzOnBURaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:18:06.755164Z","bundle_sha256":"c6b411a0726cb9b3889081af3675b1a2c4ffb974018d3d4f02327109103ae482"}}