{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FJ4VJMEWN46OWPHKOKVD3AKVHO","short_pith_number":"pith:FJ4VJMEW","canonical_record":{"source":{"id":"1803.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-26T04:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"60c8d29582e3ece70c8645974af559a25421be6d6c01034db6138ffbe67728cc","abstract_canon_sha256":"1afd6556b6fb8b57f41e9a031c30c63291f0ab4b68520ef5b928d3e395cd9189"},"schema_version":"1.0"},"canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","source":{"kind":"arxiv","id":"1803.09405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09405","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09405v1","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09405","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"FJ4VJMEWN46O","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FJ4VJMEWN46OWPHK","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FJ4VJMEW","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FJ4VJMEWN46OWPHKOKVD3AKVHO","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-26T04:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"60c8d29582e3ece70c8645974af559a25421be6d6c01034db6138ffbe67728cc","abstract_canon_sha256":"1afd6556b6fb8b57f41e9a031c30c63291f0ab4b68520ef5b928d3e395cd9189"},"schema_version":"1.0"},"canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:11.711970Z","signature_b64":"3DtbQwUikYQbS3+f9UfWqqrS01e9deyAhCaYqE1T8RSleuwaheudjQMVhayg6MEvO+81UMiF+BEl242kTX5nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","last_reissued_at":"2026-05-18T00:20:11.711327Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:11.711327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09405","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":"2026-05-18T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qGYNAHFAZCI4pJrACnrEky46z0OuLSZxUCeGhq2R64izQQht4DHIVTBs1O34vQk8x8eziZOXPa+kc3JJao5ABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:20:14.813032Z"},"content_sha256":"12a4dde057fe4a054f8578b832634831a17a307c02bb369ac310a16be3ae9f92","schema_version":"1.0","event_id":"sha256:12a4dde057fe4a054f8578b832634831a17a307c02bb369ac310a16be3ae9f92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FJ4VJMEWN46OWPHKOKVD3AKVHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Identification of Closely-related Indian Languages: Resources and Experiments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdul Basit, Atul Kr. Ojha, Bornini Lahiri, Deepak Alok, Mayank Jain, Ritesh Kumar, Yogesh Dawer","submitted_at":"2018-03-26T04:02:00Z","abstract_excerpt":"In this paper, we discuss an attempt to develop an automatic language identification system for 5 closely-related Indo-Aryan languages of India, Awadhi, Bhojpuri, Braj, Hindi and Magahi. We have compiled a comparable corpora of varying length for these languages from various resources. We discuss the method of creation of these corpora in detail. Using these corpora, a language identification system was developed, which currently gives state of the art accuracy of 96.48\\%. We also used these corpora to study the similarity between the 5 languages at the lexical level, which is the first data-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09405","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":"2026-05-18T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B0L33TQgMvMn71Pfb0K4VUr9z9mdgYD08seD4rnjAk2nvkezrPjXQugQt7xtuv6rCAJ4O0aWmepEbbvm+PtsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:20:14.813402Z"},"content_sha256":"b3a04c7e266a07de7d845c0d2a6c464aab17e4d91fc823284b49d4d55cc97233","schema_version":"1.0","event_id":"sha256:b3a04c7e266a07de7d845c0d2a6c464aab17e4d91fc823284b49d4d55cc97233"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/bundle.json","state_url":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/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":"2026-06-01T16:20:14Z","links":{"resolver":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO","bundle":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/bundle.json","state":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FJ4VJMEWN46OWPHKOKVD3AKVHO","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":"1afd6556b6fb8b57f41e9a031c30c63291f0ab4b68520ef5b928d3e395cd9189","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-26T04:02:00Z","title_canon_sha256":"60c8d29582e3ece70c8645974af559a25421be6d6c01034db6138ffbe67728cc"},"schema_version":"1.0","source":{"id":"1803.09405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09405","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09405v1","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09405","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"FJ4VJMEWN46O","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FJ4VJMEWN46OWPHK","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FJ4VJMEW","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:b3a04c7e266a07de7d845c0d2a6c464aab17e4d91fc823284b49d4d55cc97233","target":"graph","created_at":"2026-05-18T00:20:11Z","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 this paper, we discuss an attempt to develop an automatic language identification system for 5 closely-related Indo-Aryan languages of India, Awadhi, Bhojpuri, Braj, Hindi and Magahi. We have compiled a comparable corpora of varying length for these languages from various resources. We discuss the method of creation of these corpora in detail. Using these corpora, a language identification system was developed, which currently gives state of the art accuracy of 96.48\\%. We also used these corpora to study the similarity between the 5 languages at the lexical level, which is the first data-b","authors_text":"Abdul Basit, Atul Kr. Ojha, Bornini Lahiri, Deepak Alok, Mayank Jain, Ritesh Kumar, Yogesh Dawer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-26T04:02:00Z","title":"Automatic Identification of Closely-related Indian Languages: Resources and Experiments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09405","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":"sha256:12a4dde057fe4a054f8578b832634831a17a307c02bb369ac310a16be3ae9f92","target":"record","created_at":"2026-05-18T00:20:11Z","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":"1afd6556b6fb8b57f41e9a031c30c63291f0ab4b68520ef5b928d3e395cd9189","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-26T04:02:00Z","title_canon_sha256":"60c8d29582e3ece70c8645974af559a25421be6d6c01034db6138ffbe67728cc"},"schema_version":"1.0","source":{"id":"1803.09405","kind":"arxiv","version":1}},"canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","first_computed_at":"2026-05-18T00:20:11.711327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:11.711327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3DtbQwUikYQbS3+f9UfWqqrS01e9deyAhCaYqE1T8RSleuwaheudjQMVhayg6MEvO+81UMiF+BEl242kTX5nCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:11.711970Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12a4dde057fe4a054f8578b832634831a17a307c02bb369ac310a16be3ae9f92","sha256:b3a04c7e266a07de7d845c0d2a6c464aab17e4d91fc823284b49d4d55cc97233"],"state_sha256":"92cb88430b1d2c6cafdef859a526c63665d6e805470550319e0a64d6435db369"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50TR5jO56nfqsYSDTi5oVylouN0S6ZWEU7DsrQc7LM5Q4BJXcQmyqYvhTOUlMosdLHD06vQHWb+6vVNbnfz+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:20:14.815451Z","bundle_sha256":"2e62770a839b75fdeb9fe3b1c9673bd46ee1616b1071a701a1fd7a4b781084a2"}}