{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:IH2Q5YKACKP7RWIT3NW6F5GD3X","short_pith_number":"pith:IH2Q5YKA","canonical_record":{"source":{"id":"1405.0546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-03T01:41:27Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"09fa8819d08753259c8f5a25fda6f220a868852285fb612911ab1f46a6d01d7c","abstract_canon_sha256":"9d4d0f99a18e92bb400bb6948be4176d3c1a6db1f4909d11d52ba5c99a20edd6"},"schema_version":"1.0"},"canonical_sha256":"41f50ee140129ff8d913db6de2f4c3ddfa933677187e80a4ce73c5313d0d57c9","source":{"kind":"arxiv","id":"1405.0546","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.0546","created_at":"2026-05-18T02:52:13Z"},{"alias_kind":"arxiv_version","alias_value":"1405.0546v2","created_at":"2026-05-18T02:52:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.0546","created_at":"2026-05-18T02:52:13Z"},{"alias_kind":"pith_short_12","alias_value":"IH2Q5YKACKP7","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"IH2Q5YKACKP7RWIT","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"IH2Q5YKA","created_at":"2026-05-18T12:28:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:IH2Q5YKACKP7RWIT3NW6F5GD3X","target":"record","payload":{"canonical_record":{"source":{"id":"1405.0546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-03T01:41:27Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"09fa8819d08753259c8f5a25fda6f220a868852285fb612911ab1f46a6d01d7c","abstract_canon_sha256":"9d4d0f99a18e92bb400bb6948be4176d3c1a6db1f4909d11d52ba5c99a20edd6"},"schema_version":"1.0"},"canonical_sha256":"41f50ee140129ff8d913db6de2f4c3ddfa933677187e80a4ce73c5313d0d57c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:52:13.795534Z","signature_b64":"ifgDkG9GllvxULeD+ykgrc913t/ghRDYpaXmku4KFJivZURhHwuqewE6uH6hL99b9KYzUbloG+LeTZsBhyZ/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41f50ee140129ff8d913db6de2f4c3ddfa933677187e80a4ce73c5313d0d57c9","last_reissued_at":"2026-05-18T02:52:13.795028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:52:13.795028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.0546","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":"2026-05-18T02:52:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rw9vk6v8MlHhK1lPQ+AuIFGbWhf+VGlMci8eln0YvA2ohg1zuKIrmetq5kasSiwmuIxfghUj5NLb9CB6vkxlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T03:00:06.484029Z"},"content_sha256":"ca90143bf938545b2ab2daa9ec8ce05205ec71092230fe6aa9fcd6423622a50f","schema_version":"1.0","event_id":"sha256:ca90143bf938545b2ab2daa9ec8ce05205ec71092230fe6aa9fcd6423622a50f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:IH2Q5YKACKP7RWIT3NW6F5GD3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kaggle LSHTC4 Winning Solution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Albert Bifet, Antti Puurula, Jesse Read","submitted_at":"2014-05-03T01:41:27Z","abstract_excerpt":"Our winning submission to the 2014 Kaggle competition for Large Scale Hierarchical Text Classification (LSHTC) consists mostly of an ensemble of sparse generative models extending Multinomial Naive Bayes. The base-classifiers consist of hierarchically smoothed models combining document, label, and hierarchy level Multinomials, with feature pre-processing using variants of TF-IDF and BM25. Additional diversification is introduced by different types of folds and random search optimization for different measures. The ensemble algorithm optimizes macroFscore by predicting the documents for each la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.0546","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":"2026-05-18T02:52:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXkOI+NVsyVUV8jWbuEFdTlQE5h01U5BR4IpambUf8dHF2ubFXAEI6Pd08P3iL9H3q6TtOZ46FuX5WHdstHrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T03:00:06.484399Z"},"content_sha256":"b968131b3bef53050199c9b1e44b0dae9088f5f7db5bec766f6b0a9d7e465736","schema_version":"1.0","event_id":"sha256:b968131b3bef53050199c9b1e44b0dae9088f5f7db5bec766f6b0a9d7e465736"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X/bundle.json","state_url":"https://pith.science/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X/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":"2026-06-29T03:00:06Z","links":{"resolver":"https://pith.science/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X","bundle":"https://pith.science/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X/bundle.json","state":"https://pith.science/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IH2Q5YKACKP7RWIT3NW6F5GD3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:IH2Q5YKACKP7RWIT3NW6F5GD3X","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":"9d4d0f99a18e92bb400bb6948be4176d3c1a6db1f4909d11d52ba5c99a20edd6","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-03T01:41:27Z","title_canon_sha256":"09fa8819d08753259c8f5a25fda6f220a868852285fb612911ab1f46a6d01d7c"},"schema_version":"1.0","source":{"id":"1405.0546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.0546","created_at":"2026-05-18T02:52:13Z"},{"alias_kind":"arxiv_version","alias_value":"1405.0546v2","created_at":"2026-05-18T02:52:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.0546","created_at":"2026-05-18T02:52:13Z"},{"alias_kind":"pith_short_12","alias_value":"IH2Q5YKACKP7","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"IH2Q5YKACKP7RWIT","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"IH2Q5YKA","created_at":"2026-05-18T12:28:33Z"}],"graph_snapshots":[{"event_id":"sha256:b968131b3bef53050199c9b1e44b0dae9088f5f7db5bec766f6b0a9d7e465736","target":"graph","created_at":"2026-05-18T02:52:13Z","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":"Our winning submission to the 2014 Kaggle competition for Large Scale Hierarchical Text Classification (LSHTC) consists mostly of an ensemble of sparse generative models extending Multinomial Naive Bayes. The base-classifiers consist of hierarchically smoothed models combining document, label, and hierarchy level Multinomials, with feature pre-processing using variants of TF-IDF and BM25. Additional diversification is introduced by different types of folds and random search optimization for different measures. The ensemble algorithm optimizes macroFscore by predicting the documents for each la","authors_text":"Albert Bifet, Antti Puurula, Jesse Read","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-03T01:41:27Z","title":"Kaggle LSHTC4 Winning Solution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.0546","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:ca90143bf938545b2ab2daa9ec8ce05205ec71092230fe6aa9fcd6423622a50f","target":"record","created_at":"2026-05-18T02:52:13Z","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":"9d4d0f99a18e92bb400bb6948be4176d3c1a6db1f4909d11d52ba5c99a20edd6","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-05-03T01:41:27Z","title_canon_sha256":"09fa8819d08753259c8f5a25fda6f220a868852285fb612911ab1f46a6d01d7c"},"schema_version":"1.0","source":{"id":"1405.0546","kind":"arxiv","version":2}},"canonical_sha256":"41f50ee140129ff8d913db6de2f4c3ddfa933677187e80a4ce73c5313d0d57c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41f50ee140129ff8d913db6de2f4c3ddfa933677187e80a4ce73c5313d0d57c9","first_computed_at":"2026-05-18T02:52:13.795028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:52:13.795028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifgDkG9GllvxULeD+ykgrc913t/ghRDYpaXmku4KFJivZURhHwuqewE6uH6hL99b9KYzUbloG+LeTZsBhyZ/AA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:52:13.795534Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.0546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca90143bf938545b2ab2daa9ec8ce05205ec71092230fe6aa9fcd6423622a50f","sha256:b968131b3bef53050199c9b1e44b0dae9088f5f7db5bec766f6b0a9d7e465736"],"state_sha256":"08e90f38838804ec4589fa93e4e2517354f82b5067db0a3b3c0c07b0e1165009"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVt0VqwvgykmcCY4dCs8frdNYHGtuu1CeMoQVjzduWi1vInR9qkW76ICZe1cywCbZ3jUFUvcnitpm1K0tFT/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T03:00:06.486283Z","bundle_sha256":"d9c561f23ac2711c2b89336cd26efd06e49d4e824921dbbe73b0194b2dbc6ff4"}}