{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:FLZDTNXD3D6WFWTJN2ZBLZDC3T","short_pith_number":"pith:FLZDTNXD","canonical_record":{"source":{"id":"1610.00031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-30T20:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"9e9ef6b68bdacf9f9c73a0bd1d6d21802c09f44cb34f02778e0239dc5eb70842","abstract_canon_sha256":"98ae3edbb5fe7197fae76d81065875b765baa37954a0fa69319ed28b8283f45a"},"schema_version":"1.0"},"canonical_sha256":"2af239b6e3d8fd62da696eb215e462dcd17eba8ddae02e558669decbe9f8ef8e","source":{"kind":"arxiv","id":"1610.00031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00031","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00031v1","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00031","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"FLZDTNXD3D6W","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FLZDTNXD3D6WFWTJ","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FLZDTNXD","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:FLZDTNXD3D6WFWTJN2ZBLZDC3T","target":"record","payload":{"canonical_record":{"source":{"id":"1610.00031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-30T20:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"9e9ef6b68bdacf9f9c73a0bd1d6d21802c09f44cb34f02778e0239dc5eb70842","abstract_canon_sha256":"98ae3edbb5fe7197fae76d81065875b765baa37954a0fa69319ed28b8283f45a"},"schema_version":"1.0"},"canonical_sha256":"2af239b6e3d8fd62da696eb215e462dcd17eba8ddae02e558669decbe9f8ef8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:32.077779Z","signature_b64":"CprYiA31lpvjVSKYNBq3UKQEx8XrRxGo9sN8f35qNn1td5xFddwDYUXhTx1hVJv7yBJFHW20wVC3oaOA39vlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2af239b6e3d8fd62da696eb215e462dcd17eba8ddae02e558669decbe9f8ef8e","last_reissued_at":"2026-05-18T01:03:32.077256Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:32.077256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.00031","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":"2026-05-18T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QlpQ5FrH5irxHhpJQx/3MbnBi/T/9qnriBwlTabeSh3q3VmHqeRlHheuDZ0fHSXZxKAJAS2HmzSFcB7YY/3hAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:59:41.902079Z"},"content_sha256":"2122150d37176c45e3fe8af10f16b9984a0ff1603603c7e6d55b8b57dc470bbe","schema_version":"1.0","event_id":"sha256:2122150d37176c45e3fe8af10f16b9984a0ff1603603c7e6d55b8b57dc470bbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:FLZDTNXD3D6WFWTJN2ZBLZDC3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discriminating Similar Languages: Evaluations and Explorations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cyril Goutte, Marcos Zampieri, Serge L\\'eger, Shervin Malmasi","submitted_at":"2016-09-30T20:57:52Z","abstract_excerpt":"We present an analysis of the performance of machine learning classifiers on discriminating between similar languages and language varieties. We carried out a number of experiments using the results of the two editions of the Discriminating between Similar Languages (DSL) shared task. We investigate the progress made between the two tasks, estimate an upper bound on possible performance using ensemble and oracle combination, and provide learning curves to help us understand which languages are more challenging. A number of difficult sentences are identified and investigated further with human "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00031","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":"2026-05-18T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6RI+QboeNsei8y9mFAGsU4S/T57OmWYRpUZ4biU68IvAuz5V+PbMLb3gXdTSxa1Yyym6PlPZJ/ZS567g+37Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:59:41.902697Z"},"content_sha256":"35d9ff475ce186a9d5cc573fa8a6fd6b7b0e3405e9f6c2307efef310225df86f","schema_version":"1.0","event_id":"sha256:35d9ff475ce186a9d5cc573fa8a6fd6b7b0e3405e9f6c2307efef310225df86f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T/bundle.json","state_url":"https://pith.science/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T/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":"2026-06-07T16:59:41Z","links":{"resolver":"https://pith.science/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T","bundle":"https://pith.science/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T/bundle.json","state":"https://pith.science/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FLZDTNXD3D6WFWTJN2ZBLZDC3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:FLZDTNXD3D6WFWTJN2ZBLZDC3T","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":"98ae3edbb5fe7197fae76d81065875b765baa37954a0fa69319ed28b8283f45a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-30T20:57:52Z","title_canon_sha256":"9e9ef6b68bdacf9f9c73a0bd1d6d21802c09f44cb34f02778e0239dc5eb70842"},"schema_version":"1.0","source":{"id":"1610.00031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00031","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00031v1","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00031","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"FLZDTNXD3D6W","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FLZDTNXD3D6WFWTJ","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FLZDTNXD","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:35d9ff475ce186a9d5cc573fa8a6fd6b7b0e3405e9f6c2307efef310225df86f","target":"graph","created_at":"2026-05-18T01:03:32Z","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 present an analysis of the performance of machine learning classifiers on discriminating between similar languages and language varieties. We carried out a number of experiments using the results of the two editions of the Discriminating between Similar Languages (DSL) shared task. We investigate the progress made between the two tasks, estimate an upper bound on possible performance using ensemble and oracle combination, and provide learning curves to help us understand which languages are more challenging. A number of difficult sentences are identified and investigated further with human ","authors_text":"Cyril Goutte, Marcos Zampieri, Serge L\\'eger, Shervin Malmasi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-30T20:57:52Z","title":"Discriminating Similar Languages: Evaluations and Explorations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00031","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":"sha256:2122150d37176c45e3fe8af10f16b9984a0ff1603603c7e6d55b8b57dc470bbe","target":"record","created_at":"2026-05-18T01:03:32Z","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":"98ae3edbb5fe7197fae76d81065875b765baa37954a0fa69319ed28b8283f45a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-30T20:57:52Z","title_canon_sha256":"9e9ef6b68bdacf9f9c73a0bd1d6d21802c09f44cb34f02778e0239dc5eb70842"},"schema_version":"1.0","source":{"id":"1610.00031","kind":"arxiv","version":1}},"canonical_sha256":"2af239b6e3d8fd62da696eb215e462dcd17eba8ddae02e558669decbe9f8ef8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2af239b6e3d8fd62da696eb215e462dcd17eba8ddae02e558669decbe9f8ef8e","first_computed_at":"2026-05-18T01:03:32.077256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:32.077256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CprYiA31lpvjVSKYNBq3UKQEx8XrRxGo9sN8f35qNn1td5xFddwDYUXhTx1hVJv7yBJFHW20wVC3oaOA39vlCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:32.077779Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.00031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2122150d37176c45e3fe8af10f16b9984a0ff1603603c7e6d55b8b57dc470bbe","sha256:35d9ff475ce186a9d5cc573fa8a6fd6b7b0e3405e9f6c2307efef310225df86f"],"state_sha256":"dab66f1299b43dec8bf9578a088a91070543ab517c0081e7da9f81b264ecb8ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgWvye69wE8k47873CUwSvUOQSK3tDVsMweZFiA/mOzHK1apegeynRcrVTxuWNs2FCwGJKhhiTPS1hpfcQyiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:59:41.906230Z","bundle_sha256":"725a44391994d1ddf64e5e5b46e1588dea4e4bb9c1bce88fe4ba5aa96ee4ddfa"}}