{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MNROH535DY5KRB5F2T4FWIKGN3","short_pith_number":"pith:MNROH535","canonical_record":{"source":{"id":"1901.00439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-25T00:31:22Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"ea0a16c51c5cffdcd3e6699e4791cd13732a32be79c317408ee1724f79aa3f9e","abstract_canon_sha256":"bea7174fc4479c1d5952e8b028e6b0461bfad06ef4a10ef50ffb6a0fa935c301"},"schema_version":"1.0"},"canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","source":{"kind":"arxiv","id":"1901.00439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00439","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00439v1","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00439","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"MNROH535DY5K","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNROH535DY5KRB5F","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNROH535","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MNROH535DY5KRB5F2T4FWIKGN3","target":"record","payload":{"canonical_record":{"source":{"id":"1901.00439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-25T00:31:22Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"ea0a16c51c5cffdcd3e6699e4791cd13732a32be79c317408ee1724f79aa3f9e","abstract_canon_sha256":"bea7174fc4479c1d5952e8b028e6b0461bfad06ef4a10ef50ffb6a0fa935c301"},"schema_version":"1.0"},"canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:03.859960Z","signature_b64":"uzffVGohuNyUMGsDOgACCds2lrgNyrUDxm2bfryRV4xkRwDcjJJXaOAv2T+8yUbmNQP87b9LdSTCPzRbjGusCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","last_reissued_at":"2026-05-17T23:57:03.859356Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:03.859356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.00439","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":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBBvNb+GwncJdoGRnMfsXk8z4cPDvIvHRNTf8o0dGNvmUvfCUvCy/jdgp9Mbc6bTcTW5+LP5fOoVdtZ/tkN5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T18:51:59.381443Z"},"content_sha256":"8298e8b4520b8158b335e588ea20bb977e6a67cd77c646beee7a51de9a4e9f99","schema_version":"1.0","event_id":"sha256:8298e8b4520b8158b335e588ea20bb977e6a67cd77c646beee7a51de9a4e9f99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MNROH535DY5KRB5F2T4FWIKGN3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Representation Learning for Clustering of Health Tweets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Oguzhan Gencoglu","submitted_at":"2018-12-25T00:31:22Z","abstract_excerpt":"Twitter has been a prominent social media platform for mining population-level health data and accurate clustering of health-related tweets into topics is important for extracting relevant health insights. In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering. We compare our method to several conventional tweet representation methods including bag-of-words, term frequency-inverse document frequency, Latent Dirichlet Allocation and Non-negative Matrix Factorization with 3 different clustering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00439","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":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6il1EwGzf1iqcYPkpu9MB6gWPUhyIcEMYXG/w/T/Go/krw7TNnDSofhKzL6jTUQY/w5jI5ybO44vGdl384EAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T18:51:59.381808Z"},"content_sha256":"6bd9bc003aabddea1594d2077ce2c240bc2ca4bb55837ed16cc11a4efedecab6","schema_version":"1.0","event_id":"sha256:6bd9bc003aabddea1594d2077ce2c240bc2ca4bb55837ed16cc11a4efedecab6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/bundle.json","state_url":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNROH535DY5KRB5F2T4FWIKGN3/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":"2026-06-28T18:51:59Z","links":{"resolver":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3","bundle":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/bundle.json","state":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNROH535DY5KRB5F2T4FWIKGN3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MNROH535DY5KRB5F2T4FWIKGN3","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":"bea7174fc4479c1d5952e8b028e6b0461bfad06ef4a10ef50ffb6a0fa935c301","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-25T00:31:22Z","title_canon_sha256":"ea0a16c51c5cffdcd3e6699e4791cd13732a32be79c317408ee1724f79aa3f9e"},"schema_version":"1.0","source":{"id":"1901.00439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00439","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00439v1","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00439","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"MNROH535DY5K","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNROH535DY5KRB5F","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNROH535","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:6bd9bc003aabddea1594d2077ce2c240bc2ca4bb55837ed16cc11a4efedecab6","target":"graph","created_at":"2026-05-17T23:57:03Z","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":"Twitter has been a prominent social media platform for mining population-level health data and accurate clustering of health-related tweets into topics is important for extracting relevant health insights. In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering. We compare our method to several conventional tweet representation methods including bag-of-words, term frequency-inverse document frequency, Latent Dirichlet Allocation and Non-negative Matrix Factorization with 3 different clustering ","authors_text":"Oguzhan Gencoglu","cross_cats":["cs.IR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-25T00:31:22Z","title":"Deep Representation Learning for Clustering of Health Tweets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00439","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":"sha256:8298e8b4520b8158b335e588ea20bb977e6a67cd77c646beee7a51de9a4e9f99","target":"record","created_at":"2026-05-17T23:57:03Z","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":"bea7174fc4479c1d5952e8b028e6b0461bfad06ef4a10ef50ffb6a0fa935c301","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-25T00:31:22Z","title_canon_sha256":"ea0a16c51c5cffdcd3e6699e4791cd13732a32be79c317408ee1724f79aa3f9e"},"schema_version":"1.0","source":{"id":"1901.00439","kind":"arxiv","version":1}},"canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","first_computed_at":"2026-05-17T23:57:03.859356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:03.859356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uzffVGohuNyUMGsDOgACCds2lrgNyrUDxm2bfryRV4xkRwDcjJJXaOAv2T+8yUbmNQP87b9LdSTCPzRbjGusCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:03.859960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.00439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8298e8b4520b8158b335e588ea20bb977e6a67cd77c646beee7a51de9a4e9f99","sha256:6bd9bc003aabddea1594d2077ce2c240bc2ca4bb55837ed16cc11a4efedecab6"],"state_sha256":"79e0d2ada370b3b675624303ed0eb2a7155ce6f8a81f1dae1057b61dc4d3e96b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2iddlEDpLBhKZ3JHrY1F7/4vWjuPsn8q0wJbJbQq74xhMtPL3cBR+cyJkFyZHBscHhgOfNNnM+TXlKpRL27AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T18:51:59.383878Z","bundle_sha256":"da7aa34951be2eb0d6b49d625c7c2ff4fab9bd533a9e13cea2305cf091825a5e"}}