{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OD4ISSGGA6YA4EU3266VIKINI2","short_pith_number":"pith:OD4ISSGG","canonical_record":{"source":{"id":"1603.09164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2016-03-30T13:00:15Z","cross_cats_sorted":[],"title_canon_sha256":"a4b1c01c2ffad39e06ae61dbca661cabecdcbaa0de1161349544150a7e108002","abstract_canon_sha256":"5091d9063138487120b529077fa4020e6fdf38a3ea8bca526b38ebbf372811d1"},"schema_version":"1.0"},"canonical_sha256":"70f88948c607b00e129bd7bd54290d468319306ee5eb519b14d9c42e7b69f6f4","source":{"kind":"arxiv","id":"1603.09164","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.09164","created_at":"2026-05-18T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"1603.09164v1","created_at":"2026-05-18T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09164","created_at":"2026-05-18T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"OD4ISSGGA6YA","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OD4ISSGGA6YA4EU3","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OD4ISSGG","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OD4ISSGGA6YA4EU3266VIKINI2","target":"record","payload":{"canonical_record":{"source":{"id":"1603.09164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2016-03-30T13:00:15Z","cross_cats_sorted":[],"title_canon_sha256":"a4b1c01c2ffad39e06ae61dbca661cabecdcbaa0de1161349544150a7e108002","abstract_canon_sha256":"5091d9063138487120b529077fa4020e6fdf38a3ea8bca526b38ebbf372811d1"},"schema_version":"1.0"},"canonical_sha256":"70f88948c607b00e129bd7bd54290d468319306ee5eb519b14d9c42e7b69f6f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:01.271295Z","signature_b64":"3wYVIM3/LbsmZE0lqsLvhLsuE9f+ewtPx2LtPkazqrGgk4cahWuQl0jOk76kwo9S82a9K5cdr7EgIA01lH7nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70f88948c607b00e129bd7bd54290d468319306ee5eb519b14d9c42e7b69f6f4","last_reissued_at":"2026-05-18T01:18:01.270657Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:01.270657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.09164","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":"2026-05-18T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFMOsjYoOAxFRYqJajzxmcbBUPDuO+//xe4PYZlZqDgZejanR9uZPp2yDDB2xpV1Ddsu8uhJs9rm8TnbSEfSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T04:36:32.632896Z"},"content_sha256":"8d86ec709c5926303c9b49ef3c91523c91c62e20f61d609231208ef3fe197a23","schema_version":"1.0","event_id":"sha256:8d86ec709c5926303c9b49ef3c91523c91c62e20f61d609231208ef3fe197a23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OD4ISSGGA6YA4EU3266VIKINI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spider and the Flies : Focused Crawling on Tumblr to Detect Hate Promoting Communities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Ashish Sureka, Swati Agarwal","submitted_at":"2016-03-30T13:00:15Z","abstract_excerpt":"Tumblr is one of the largest and most popular microblogging website on the Internet. Studies shows that due to high reachability among viewers, low publication barriers and social networking connectivity, microblogging websites are being misused as a platform to post hateful speech and recruiting new members by existing extremist groups. Manual identification of such posts and communities is overwhelmingly impractical due to large amount of posts and blogs being published every day. We propose a topic based web crawler primarily consisting of multiple phases: training a text classifier model c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09164","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":"2026-05-18T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0Xeh7IaTHMCveAM04HPKlE1c2C6mpe6lkaX1I6jBHSj5in8Np56fhDRoFaNabDhQYrR1FLZajdTvsi0TBEHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T04:36:32.633233Z"},"content_sha256":"e206a585b5318ac90a8b92fbac52f6784d26d9cc8a8a2f66db8a92250f96efca","schema_version":"1.0","event_id":"sha256:e206a585b5318ac90a8b92fbac52f6784d26d9cc8a8a2f66db8a92250f96efca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OD4ISSGGA6YA4EU3266VIKINI2/bundle.json","state_url":"https://pith.science/pith/OD4ISSGGA6YA4EU3266VIKINI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OD4ISSGGA6YA4EU3266VIKINI2/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":"2026-06-07T04:36:32Z","links":{"resolver":"https://pith.science/pith/OD4ISSGGA6YA4EU3266VIKINI2","bundle":"https://pith.science/pith/OD4ISSGGA6YA4EU3266VIKINI2/bundle.json","state":"https://pith.science/pith/OD4ISSGGA6YA4EU3266VIKINI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OD4ISSGGA6YA4EU3266VIKINI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OD4ISSGGA6YA4EU3266VIKINI2","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":"5091d9063138487120b529077fa4020e6fdf38a3ea8bca526b38ebbf372811d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2016-03-30T13:00:15Z","title_canon_sha256":"a4b1c01c2ffad39e06ae61dbca661cabecdcbaa0de1161349544150a7e108002"},"schema_version":"1.0","source":{"id":"1603.09164","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.09164","created_at":"2026-05-18T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"1603.09164v1","created_at":"2026-05-18T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09164","created_at":"2026-05-18T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"OD4ISSGGA6YA","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OD4ISSGGA6YA4EU3","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OD4ISSGG","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:e206a585b5318ac90a8b92fbac52f6784d26d9cc8a8a2f66db8a92250f96efca","target":"graph","created_at":"2026-05-18T01:18:01Z","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":"Tumblr is one of the largest and most popular microblogging website on the Internet. Studies shows that due to high reachability among viewers, low publication barriers and social networking connectivity, microblogging websites are being misused as a platform to post hateful speech and recruiting new members by existing extremist groups. Manual identification of such posts and communities is overwhelmingly impractical due to large amount of posts and blogs being published every day. We propose a topic based web crawler primarily consisting of multiple phases: training a text classifier model c","authors_text":"Ashish Sureka, Swati Agarwal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2016-03-30T13:00:15Z","title":"Spider and the Flies : Focused Crawling on Tumblr to Detect Hate Promoting Communities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09164","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":"sha256:8d86ec709c5926303c9b49ef3c91523c91c62e20f61d609231208ef3fe197a23","target":"record","created_at":"2026-05-18T01:18:01Z","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":"5091d9063138487120b529077fa4020e6fdf38a3ea8bca526b38ebbf372811d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2016-03-30T13:00:15Z","title_canon_sha256":"a4b1c01c2ffad39e06ae61dbca661cabecdcbaa0de1161349544150a7e108002"},"schema_version":"1.0","source":{"id":"1603.09164","kind":"arxiv","version":1}},"canonical_sha256":"70f88948c607b00e129bd7bd54290d468319306ee5eb519b14d9c42e7b69f6f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70f88948c607b00e129bd7bd54290d468319306ee5eb519b14d9c42e7b69f6f4","first_computed_at":"2026-05-18T01:18:01.270657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:01.270657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wYVIM3/LbsmZE0lqsLvhLsuE9f+ewtPx2LtPkazqrGgk4cahWuQl0jOk76kwo9S82a9K5cdr7EgIA01lH7nAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:01.271295Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.09164","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d86ec709c5926303c9b49ef3c91523c91c62e20f61d609231208ef3fe197a23","sha256:e206a585b5318ac90a8b92fbac52f6784d26d9cc8a8a2f66db8a92250f96efca"],"state_sha256":"4d6cf53f62b416d6e938b9b2977810282814965e85389b3913a6e3e8aee0cec5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ora070pdtUQZ09Uuuq0PJ/YJwQyAZrryPg0fm7ug0jY7Rni95fuoDCZLbwpn8MGJfjBn6Mmb+489jcj/t17mBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T04:36:32.635086Z","bundle_sha256":"f316653b6e3956a145cf2db514b735bced447ce5a6fcc6659ca476c26e7061c1"}}