{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LMHJIGU4X46FNT6N5JTCBTBZAC","short_pith_number":"pith:LMHJIGU4","canonical_record":{"source":{"id":"1712.06427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-18T14:39:57Z","cross_cats_sorted":[],"title_canon_sha256":"a29f6df0c028e8346990c0bd0e5c8fb93cd1fce93f872e42b3c9fce8f8ed9105","abstract_canon_sha256":"acf8a0a1ff8061bae779e7181a6df8fb2406442ff0da73ac2971d844dfd86690"},"schema_version":"1.0"},"canonical_sha256":"5b0e941a9cbf3c56cfcdea6620cc3900b81345229ee8eae26d153cd85f6aa605","source":{"kind":"arxiv","id":"1712.06427","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06427","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06427v2","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06427","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"LMHJIGU4X46F","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LMHJIGU4X46FNT6N","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LMHJIGU4","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LMHJIGU4X46FNT6N5JTCBTBZAC","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-18T14:39:57Z","cross_cats_sorted":[],"title_canon_sha256":"a29f6df0c028e8346990c0bd0e5c8fb93cd1fce93f872e42b3c9fce8f8ed9105","abstract_canon_sha256":"acf8a0a1ff8061bae779e7181a6df8fb2406442ff0da73ac2971d844dfd86690"},"schema_version":"1.0"},"canonical_sha256":"5b0e941a9cbf3c56cfcdea6620cc3900b81345229ee8eae26d153cd85f6aa605","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:08.877369Z","signature_b64":"h2nA3KBI0uIDtMp08gwdHB8cwYsrjz7tfxHn+6dFDon7zk2Ndb1Wp13gVGph0Z13ZSTk4xLiAnAa23TUyoU/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b0e941a9cbf3c56cfcdea6620cc3900b81345229ee8eae26d153cd85f6aa605","last_reissued_at":"2026-05-18T00:27:08.876679Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:08.876679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06427","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":"2026-05-18T00:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/hALOcYBQfp5VjUMIej4sQoa+4FDeD87/K02jlWjL5+FTCF1OE3x2opCA2+ip/Ws2XyMJpQ3eMuxKVzsrJ+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:33:56.228005Z"},"content_sha256":"47911a569482e88b2dbd8df21bfb1f53650a91e1bda090a9909cf23deeb5ddbb","schema_version":"1.0","event_id":"sha256:47911a569482e88b2dbd8df21bfb1f53650a91e1bda090a9909cf23deeb5ddbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LMHJIGU4X46FNT6N5JTCBTBZAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Hate Speech in Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcos Zampieri, Shervin Malmasi","submitted_at":"2017-12-18T14:39:57Z","abstract_excerpt":"In this paper we examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by applying supervised classification methods using a recently released dataset annotated for this purpose. As features, our system uses character n-grams, word n-grams and word skip-grams. We obtain results of 78% accuracy in identifying posts across three classes. Results demonstrate that the main challenge lies in discriminating profanity and hate speech from each other. A number of directions for future work are discus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06427","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":""},"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":"2026-05-18T00:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BAeA5Cx2v3R7sE/hewMoT33d3DBIpttKal69LUM+d7malyslUlKM95XTSNIm3UG9oy9Zh1YcoW5hqz8XikbRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:33:56.228739Z"},"content_sha256":"fa87976b5cb85bfe7ac073c6a40682dd9eb61385d1f1c3cbefcc3220c17908f0","schema_version":"1.0","event_id":"sha256:fa87976b5cb85bfe7ac073c6a40682dd9eb61385d1f1c3cbefcc3220c17908f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMHJIGU4X46FNT6N5JTCBTBZAC/bundle.json","state_url":"https://pith.science/pith/LMHJIGU4X46FNT6N5JTCBTBZAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMHJIGU4X46FNT6N5JTCBTBZAC/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":"2026-06-07T21:33:56Z","links":{"resolver":"https://pith.science/pith/LMHJIGU4X46FNT6N5JTCBTBZAC","bundle":"https://pith.science/pith/LMHJIGU4X46FNT6N5JTCBTBZAC/bundle.json","state":"https://pith.science/pith/LMHJIGU4X46FNT6N5JTCBTBZAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMHJIGU4X46FNT6N5JTCBTBZAC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LMHJIGU4X46FNT6N5JTCBTBZAC","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":"acf8a0a1ff8061bae779e7181a6df8fb2406442ff0da73ac2971d844dfd86690","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-18T14:39:57Z","title_canon_sha256":"a29f6df0c028e8346990c0bd0e5c8fb93cd1fce93f872e42b3c9fce8f8ed9105"},"schema_version":"1.0","source":{"id":"1712.06427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06427","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06427v2","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06427","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"LMHJIGU4X46F","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LMHJIGU4X46FNT6N","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LMHJIGU4","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:fa87976b5cb85bfe7ac073c6a40682dd9eb61385d1f1c3cbefcc3220c17908f0","target":"graph","created_at":"2026-05-18T00:27:08Z","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 examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by applying supervised classification methods using a recently released dataset annotated for this purpose. As features, our system uses character n-grams, word n-grams and word skip-grams. We obtain results of 78% accuracy in identifying posts across three classes. Results demonstrate that the main challenge lies in discriminating profanity and hate speech from each other. A number of directions for future work are discus","authors_text":"Marcos Zampieri, Shervin Malmasi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-18T14:39:57Z","title":"Detecting Hate Speech in Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06427","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":"sha256:47911a569482e88b2dbd8df21bfb1f53650a91e1bda090a9909cf23deeb5ddbb","target":"record","created_at":"2026-05-18T00:27:08Z","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":"acf8a0a1ff8061bae779e7181a6df8fb2406442ff0da73ac2971d844dfd86690","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-18T14:39:57Z","title_canon_sha256":"a29f6df0c028e8346990c0bd0e5c8fb93cd1fce93f872e42b3c9fce8f8ed9105"},"schema_version":"1.0","source":{"id":"1712.06427","kind":"arxiv","version":2}},"canonical_sha256":"5b0e941a9cbf3c56cfcdea6620cc3900b81345229ee8eae26d153cd85f6aa605","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b0e941a9cbf3c56cfcdea6620cc3900b81345229ee8eae26d153cd85f6aa605","first_computed_at":"2026-05-18T00:27:08.876679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:08.876679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h2nA3KBI0uIDtMp08gwdHB8cwYsrjz7tfxHn+6dFDon7zk2Ndb1Wp13gVGph0Z13ZSTk4xLiAnAa23TUyoU/Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:08.877369Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47911a569482e88b2dbd8df21bfb1f53650a91e1bda090a9909cf23deeb5ddbb","sha256:fa87976b5cb85bfe7ac073c6a40682dd9eb61385d1f1c3cbefcc3220c17908f0"],"state_sha256":"7a26c4d433379cba1974fbfda130442801134dbf6ef315a56c33802b804a17b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MutKP3LFTDmX9GUyFW1nVsKrR3jJCdyX2E2TWi6mEg5VmAgzwQcm+lpx7BWpzvqyIudjuyZhTazuT3v9hi6hBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:33:56.232439Z","bundle_sha256":"3a03e9e26817a222d770e87be32e71c35f512a236f4602e19beb98d7a3c70268"}}