{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BKBOHLGO27OF6FMFSQG3T5VOHH","short_pith_number":"pith:BKBOHLGO","canonical_record":{"source":{"id":"1704.06726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-22T00:23:32Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"7692304e2914cbf34282c9e4931d99d17e796ae8e04e0979916255f260bd5709","abstract_canon_sha256":"baf67565341a3b8faa621f3ce3784452db421ecb0d7fede6016e341176596aaa"},"schema_version":"1.0"},"canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","source":{"kind":"arxiv","id":"1704.06726","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06726","created_at":"2026-05-18T00:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06726v1","created_at":"2026-05-18T00:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06726","created_at":"2026-05-18T00:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"BKBOHLGO27OF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BKBOHLGO27OF6FMF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BKBOHLGO","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BKBOHLGO27OF6FMFSQG3T5VOHH","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-22T00:23:32Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"7692304e2914cbf34282c9e4931d99d17e796ae8e04e0979916255f260bd5709","abstract_canon_sha256":"baf67565341a3b8faa621f3ce3784452db421ecb0d7fede6016e341176596aaa"},"schema_version":"1.0"},"canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:57.765996Z","signature_b64":"fy0eU1nhtJh34bKYdo5Af/VHnjgx6wlsTAEOpLK0mQAW+MztRzItlhmvAsd317Qr0RJtwA6K4/g8ehpQd8/dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","last_reissued_at":"2026-05-18T00:45:57.765381Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:57.765381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06726","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":"2026-05-18T00:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDszbHq70SsrYzHBx8v9OOiFbEmrCZLez8ps1f7xZeWaY3Z6p8I25H8AMWTvhZnD0PP61VxopbEPA7iRqffpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:56:45.263659Z"},"content_sha256":"18de25e26711899a40561f9aee11ae016464162b93012e54507c9c5631b54395","schema_version":"1.0","event_id":"sha256:18de25e26711899a40561f9aee11ae016464162b93012e54507c9c5631b54395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BKBOHLGO27OF6FMFSQG3T5VOHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distant Supervision for Topic Classification of Tweets in Curated Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Nimesh Ghelani, Salman Mohammed","submitted_at":"2017-04-22T00:23:32Z","abstract_excerpt":"We tackle the challenge of topic classification of tweets in the context of analyzing a large collection of curated streams by news outlets and other organizations to deliver relevant content to users. Our approach is novel in applying distant supervision based on semi-automatically identifying curated streams that are topically focused (for example, on politics, entertainment, or sports). These streams provide a source of labeled data to train topic classifiers that can then be applied to categorize tweets from more topically-diffuse streams. Experiments on both noisy labels and human ground-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06726","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":"2026-05-18T00:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XSsXdTyK8KNjE5EZOK+GGHaR7ka39ui2WL3q+k/gxQSmJeOmuHncRhd+ow0/LNOREkqd4hBJJVGugTzWvDf0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:56:45.264347Z"},"content_sha256":"c67b6cd954866440cd8a6b71a75431fcc6c75f5f8fc13f0126408f4cc8997949","schema_version":"1.0","event_id":"sha256:c67b6cd954866440cd8a6b71a75431fcc6c75f5f8fc13f0126408f4cc8997949"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/bundle.json","state_url":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/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":"2026-05-27T01:56:45Z","links":{"resolver":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH","bundle":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/bundle.json","state":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BKBOHLGO27OF6FMFSQG3T5VOHH","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":"baf67565341a3b8faa621f3ce3784452db421ecb0d7fede6016e341176596aaa","cross_cats_sorted":["cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-22T00:23:32Z","title_canon_sha256":"7692304e2914cbf34282c9e4931d99d17e796ae8e04e0979916255f260bd5709"},"schema_version":"1.0","source":{"id":"1704.06726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06726","created_at":"2026-05-18T00:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06726v1","created_at":"2026-05-18T00:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06726","created_at":"2026-05-18T00:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"BKBOHLGO27OF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BKBOHLGO27OF6FMF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BKBOHLGO","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:c67b6cd954866440cd8a6b71a75431fcc6c75f5f8fc13f0126408f4cc8997949","target":"graph","created_at":"2026-05-18T00:45:57Z","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 tackle the challenge of topic classification of tweets in the context of analyzing a large collection of curated streams by news outlets and other organizations to deliver relevant content to users. Our approach is novel in applying distant supervision based on semi-automatically identifying curated streams that are topically focused (for example, on politics, entertainment, or sports). These streams provide a source of labeled data to train topic classifiers that can then be applied to categorize tweets from more topically-diffuse streams. Experiments on both noisy labels and human ground-","authors_text":"Jimmy Lin, Nimesh Ghelani, Salman Mohammed","cross_cats":["cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-22T00:23:32Z","title":"Distant Supervision for Topic Classification of Tweets in Curated Streams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06726","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":"sha256:18de25e26711899a40561f9aee11ae016464162b93012e54507c9c5631b54395","target":"record","created_at":"2026-05-18T00:45:57Z","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":"baf67565341a3b8faa621f3ce3784452db421ecb0d7fede6016e341176596aaa","cross_cats_sorted":["cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-22T00:23:32Z","title_canon_sha256":"7692304e2914cbf34282c9e4931d99d17e796ae8e04e0979916255f260bd5709"},"schema_version":"1.0","source":{"id":"1704.06726","kind":"arxiv","version":1}},"canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","first_computed_at":"2026-05-18T00:45:57.765381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:57.765381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fy0eU1nhtJh34bKYdo5Af/VHnjgx6wlsTAEOpLK0mQAW+MztRzItlhmvAsd317Qr0RJtwA6K4/g8ehpQd8/dCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:57.765996Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18de25e26711899a40561f9aee11ae016464162b93012e54507c9c5631b54395","sha256:c67b6cd954866440cd8a6b71a75431fcc6c75f5f8fc13f0126408f4cc8997949"],"state_sha256":"f299465e0e984706f78ec5332a06ea8baf39c6a5931cbef59f31eb895562b893"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PzIOJhBdWywyogEa8XkqxYBWz7oofaNUnSurOCYv8H3KTxJcXFtUW4ElZwekPpbrwewMPu8QqBnjRPRTSXrkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:56:45.268071Z","bundle_sha256":"b0468b2d2a5bf05aa91063fda4f7997a12f88c217220a8ceae8ce3159966505f"}}