{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FG544H2T6ZGSYRTH3GWUITQJVW","short_pith_number":"pith:FG544H2T","canonical_record":{"source":{"id":"2004.14454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T20:02:58Z","cross_cats_sorted":[],"title_canon_sha256":"45bc3c9c478a0739c9d9ca49c68c5627f14e56487c1209665eef11910085b67d","abstract_canon_sha256":"59fb75b9925a5339d922fc7e1fe201918e3019744873e7f4ac2d7fbe7b4339d0"},"schema_version":"1.0"},"canonical_sha256":"29bbce1f53f64d2c4667d9ad444e09ada6f1c647f4c71f17ba35127217bdb21d","source":{"kind":"arxiv","id":"2004.14454","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14454","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14454v2","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14454","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"FG544H2T6ZGS","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"FG544H2T6ZGSYRTH","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"FG544H2T","created_at":"2026-07-05T03:17:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FG544H2T6ZGSYRTH3GWUITQJVW","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T20:02:58Z","cross_cats_sorted":[],"title_canon_sha256":"45bc3c9c478a0739c9d9ca49c68c5627f14e56487c1209665eef11910085b67d","abstract_canon_sha256":"59fb75b9925a5339d922fc7e1fe201918e3019744873e7f4ac2d7fbe7b4339d0"},"schema_version":"1.0"},"canonical_sha256":"29bbce1f53f64d2c4667d9ad444e09ada6f1c647f4c71f17ba35127217bdb21d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:00.267810Z","signature_b64":"AfR1kMpCh/6o1+to49ZHnxg0N1Ez+uR11US5SOTccBADHAmsraHuQlRnU2Lugy65qBKHs5tNOmh3YhA2TC8yAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29bbce1f53f64d2c4667d9ad444e09ada6f1c647f4c71f17ba35127217bdb21d","last_reissued_at":"2026-07-05T03:17:00.267408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:00.267408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14454","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jawpOoTPiLZ5jYRukoQW6yRn5oRTOuA1g/VvV9CL8FfsAfMAlvBNBRivUcRHc3Ct6DRGNZ9TOJp8rQ0eL4iXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T22:35:36.256865Z"},"content_sha256":"a42d5e34575bc1a02aa09b17ec3bcac0879cfb51f2c4e90af805f0016f665b96","schema_version":"1.0","event_id":"sha256:a42d5e34575bc1a02aa09b17ec3bcac0879cfb51f2c4e90af805f0016f665b96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FG544H2T6ZGSYRTH3GWUITQJVW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Georgi Karadzhov, Marcos Zampieri, Pepa Atanasova, Preslav Nakov, Sara Rosenthal","submitted_at":"2020-04-29T20:02:58Z","abstract_excerpt":"The widespread use of offensive content in social media has led to an abundance of research in detecting language such as hate speech, cyberbullying, and cyber-aggression. Recent work presented the OLID dataset, which follows a taxonomy for offensive language identification that provides meaningful information for understanding the type and the target of offensive messages. However, it is limited in size and it might be biased towards offensive language as it was collected using keywords. In this work, we present SOLID, an expanded dataset, where the tweets were collected in a more principled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14454","kind":"arxiv","version":2},"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/2004.14454/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":"2026-07-05T03:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R6nQTls9dK0PNB08VGZ8wLNRXPia50dZ6NPzdo7WeZ0tOqwCGeajh3vNz8XpR0Y1CpDVt50JBSDWvoPbA2NuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T22:35:36.257249Z"},"content_sha256":"ffe3edf941d7e237462ca264834caedfaf60c19afe94792167da7df8895b21b5","schema_version":"1.0","event_id":"sha256:ffe3edf941d7e237462ca264834caedfaf60c19afe94792167da7df8895b21b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FG544H2T6ZGSYRTH3GWUITQJVW/bundle.json","state_url":"https://pith.science/pith/FG544H2T6ZGSYRTH3GWUITQJVW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FG544H2T6ZGSYRTH3GWUITQJVW/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":"2026-07-27T22:35:36Z","links":{"resolver":"https://pith.science/pith/FG544H2T6ZGSYRTH3GWUITQJVW","bundle":"https://pith.science/pith/FG544H2T6ZGSYRTH3GWUITQJVW/bundle.json","state":"https://pith.science/pith/FG544H2T6ZGSYRTH3GWUITQJVW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FG544H2T6ZGSYRTH3GWUITQJVW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FG544H2T6ZGSYRTH3GWUITQJVW","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":"59fb75b9925a5339d922fc7e1fe201918e3019744873e7f4ac2d7fbe7b4339d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T20:02:58Z","title_canon_sha256":"45bc3c9c478a0739c9d9ca49c68c5627f14e56487c1209665eef11910085b67d"},"schema_version":"1.0","source":{"id":"2004.14454","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14454","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14454v2","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14454","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"FG544H2T6ZGS","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"FG544H2T6ZGSYRTH","created_at":"2026-07-05T03:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"FG544H2T","created_at":"2026-07-05T03:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:ffe3edf941d7e237462ca264834caedfaf60c19afe94792167da7df8895b21b5","target":"graph","created_at":"2026-07-05T03:17:00Z","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/2004.14454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread use of offensive content in social media has led to an abundance of research in detecting language such as hate speech, cyberbullying, and cyber-aggression. Recent work presented the OLID dataset, which follows a taxonomy for offensive language identification that provides meaningful information for understanding the type and the target of offensive messages. However, it is limited in size and it might be biased towards offensive language as it was collected using keywords. In this work, we present SOLID, an expanded dataset, where the tweets were collected in a more principled ","authors_text":"Georgi Karadzhov, Marcos Zampieri, Pepa Atanasova, Preslav Nakov, Sara Rosenthal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T20:02:58Z","title":"SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14454","kind":"arxiv","version":2},"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:a42d5e34575bc1a02aa09b17ec3bcac0879cfb51f2c4e90af805f0016f665b96","target":"record","created_at":"2026-07-05T03:17:00Z","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":"59fb75b9925a5339d922fc7e1fe201918e3019744873e7f4ac2d7fbe7b4339d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T20:02:58Z","title_canon_sha256":"45bc3c9c478a0739c9d9ca49c68c5627f14e56487c1209665eef11910085b67d"},"schema_version":"1.0","source":{"id":"2004.14454","kind":"arxiv","version":2}},"canonical_sha256":"29bbce1f53f64d2c4667d9ad444e09ada6f1c647f4c71f17ba35127217bdb21d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29bbce1f53f64d2c4667d9ad444e09ada6f1c647f4c71f17ba35127217bdb21d","first_computed_at":"2026-07-05T03:17:00.267408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:00.267408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfR1kMpCh/6o1+to49ZHnxg0N1Ez+uR11US5SOTccBADHAmsraHuQlRnU2Lugy65qBKHs5tNOmh3YhA2TC8yAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:00.267810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14454","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a42d5e34575bc1a02aa09b17ec3bcac0879cfb51f2c4e90af805f0016f665b96","sha256:ffe3edf941d7e237462ca264834caedfaf60c19afe94792167da7df8895b21b5"],"state_sha256":"5763f3ef427fb1c6beb71d708abdb83e79312b4bf81f482e2ab3f3eb2ab78ed4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8d+nfhqpStov3PnHNzVb6W5QBYD2QyjPZNkWQMVJVH4SdG05d1vTqdKyl0GawIacuR49MyejW1JT/OaaTBxAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T22:35:36.259426Z","bundle_sha256":"17c8a2296e871b56eef7eb2b4b4a89a50389e379fb7eb111a28a017a65e7fe34"}}