{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2NU6JWXJ4QTVTWASFJISJJ5B4M","short_pith_number":"pith:2NU6JWXJ","canonical_record":{"source":{"id":"1803.06390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-16T20:19:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"2945ff15e385530eb6bc3d050b1c6f8a576e7189a3cc3dc5f9f1169127db06ba","abstract_canon_sha256":"629c721ff5a4a28be7aebf37a528742fec233eb9397d163df6dab7787c588f9d"},"schema_version":"1.0"},"canonical_sha256":"d369e4dae9e42759d8122a5124a7a1e33492ecf79c0f5403cf10a5a2325b2b27","source":{"kind":"arxiv","id":"1803.06390","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06390","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06390v1","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06390","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"2NU6JWXJ4QTV","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2NU6JWXJ4QTVTWAS","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2NU6JWXJ","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2NU6JWXJ4QTVTWASFJISJJ5B4M","target":"record","payload":{"canonical_record":{"source":{"id":"1803.06390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-16T20:19:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"2945ff15e385530eb6bc3d050b1c6f8a576e7189a3cc3dc5f9f1169127db06ba","abstract_canon_sha256":"629c721ff5a4a28be7aebf37a528742fec233eb9397d163df6dab7787c588f9d"},"schema_version":"1.0"},"canonical_sha256":"d369e4dae9e42759d8122a5124a7a1e33492ecf79c0f5403cf10a5a2325b2b27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:45.990847Z","signature_b64":"BRtF4bYU4kJbcADx/vn0yS3PvAobQ7X2lhcbLa1gWwnMIVNkFnvJf0vNGZ8BCesYZ5Tn6S62vAHSaY2NUhOkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d369e4dae9e42759d8122a5124a7a1e33492ecf79c0f5403cf10a5a2325b2b27","last_reissued_at":"2026-05-18T00:20:45.990258Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:45.990258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.06390","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":"2026-05-18T00:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VP1US+GfBvVOumuFYTmLEA8qCx5v0ab7UiwibYWwCNmwx4NeoRAmbgWnqb6ZoLbIn6BJzkCOdxzaKpWwynMGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T12:51:12.374235Z"},"content_sha256":"9a83d470b25990ebc65135fed526f879dd18d8cb39d15111c5d3e06a93ac8493","schema_version":"1.0","event_id":"sha256:9a83d470b25990ebc65135fed526f879dd18d8cb39d15111c5d3e06a93ac8493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2NU6JWXJ4QTVTWASFJISJJ5B4M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corpus Statistics in Text Classification of Online Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Marina Sokolova, Victoria Bobicev","submitted_at":"2018-03-16T20:19:56Z","abstract_excerpt":"Transformation of Machine Learning (ML) from a boutique science to a generally accepted technology has increased importance of reproduction and transportability of ML studies. In the current work, we investigate how corpus characteristics of textual data sets correspond to text classification results. We work with two data sets gathered from sub-forums of an online health-related forum. Our empirical results are obtained for a multi-class sentiment analysis application."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06390","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":"2026-05-18T00:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wfFdjzmdBT9zKLmEJd8PwdIMohDAzApsxpqdmUTulaGNoV4Q5tVKnK5icOccG9sTS7Jpu57lYBYOg6Y1hni6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T12:51:12.374699Z"},"content_sha256":"8590bf79977568c1537f67a7b20b3351a426a244bd28e2575469a5ac499de5c8","schema_version":"1.0","event_id":"sha256:8590bf79977568c1537f67a7b20b3351a426a244bd28e2575469a5ac499de5c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M/bundle.json","state_url":"https://pith.science/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M/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":"2026-06-24T12:51:12Z","links":{"resolver":"https://pith.science/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M","bundle":"https://pith.science/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M/bundle.json","state":"https://pith.science/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NU6JWXJ4QTVTWASFJISJJ5B4M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2NU6JWXJ4QTVTWASFJISJJ5B4M","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":"629c721ff5a4a28be7aebf37a528742fec233eb9397d163df6dab7787c588f9d","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-16T20:19:56Z","title_canon_sha256":"2945ff15e385530eb6bc3d050b1c6f8a576e7189a3cc3dc5f9f1169127db06ba"},"schema_version":"1.0","source":{"id":"1803.06390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06390","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06390v1","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06390","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"2NU6JWXJ4QTV","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2NU6JWXJ4QTVTWAS","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2NU6JWXJ","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:8590bf79977568c1537f67a7b20b3351a426a244bd28e2575469a5ac499de5c8","target":"graph","created_at":"2026-05-18T00:20:45Z","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":"Transformation of Machine Learning (ML) from a boutique science to a generally accepted technology has increased importance of reproduction and transportability of ML studies. In the current work, we investigate how corpus characteristics of textual data sets correspond to text classification results. We work with two data sets gathered from sub-forums of an online health-related forum. Our empirical results are obtained for a multi-class sentiment analysis application.","authors_text":"Marina Sokolova, Victoria Bobicev","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-16T20:19:56Z","title":"Corpus Statistics in Text Classification of Online Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06390","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":"sha256:9a83d470b25990ebc65135fed526f879dd18d8cb39d15111c5d3e06a93ac8493","target":"record","created_at":"2026-05-18T00:20:45Z","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":"629c721ff5a4a28be7aebf37a528742fec233eb9397d163df6dab7787c588f9d","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-16T20:19:56Z","title_canon_sha256":"2945ff15e385530eb6bc3d050b1c6f8a576e7189a3cc3dc5f9f1169127db06ba"},"schema_version":"1.0","source":{"id":"1803.06390","kind":"arxiv","version":1}},"canonical_sha256":"d369e4dae9e42759d8122a5124a7a1e33492ecf79c0f5403cf10a5a2325b2b27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d369e4dae9e42759d8122a5124a7a1e33492ecf79c0f5403cf10a5a2325b2b27","first_computed_at":"2026-05-18T00:20:45.990258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:45.990258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRtF4bYU4kJbcADx/vn0yS3PvAobQ7X2lhcbLa1gWwnMIVNkFnvJf0vNGZ8BCesYZ5Tn6S62vAHSaY2NUhOkCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:45.990847Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.06390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a83d470b25990ebc65135fed526f879dd18d8cb39d15111c5d3e06a93ac8493","sha256:8590bf79977568c1537f67a7b20b3351a426a244bd28e2575469a5ac499de5c8"],"state_sha256":"a0759e25d32efabe2ee7b00867a97981ce41d81775a2d4842be7820313e286ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALHUck7Nl3gBa+YuNG/6G13scmEBge3Hehz7oXlM5Pkn7yxUi8wlEOVWLYtrTswo3tYHlRUjUq/SLmcGtBkKCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T12:51:12.377233Z","bundle_sha256":"2fa7e522af36fe9f5e1851df00ab60b9624f6a9649f6b81735005720987e1a4d"}}