{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:3TNFYTZVIY4IHCUQL2DBJV2USP","short_pith_number":"pith:3TNFYTZV","canonical_record":{"source":{"id":"1107.2462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-07-13T04:28:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e5fcb0f4fe3a9602a20dea6a2209ea6d5bab1455b488603c5c7e9623748bf04","abstract_canon_sha256":"85b919c45b0ab255483f1e253e33aead4e71e530d9d85e57462b64c369e967e8"},"schema_version":"1.0"},"canonical_sha256":"dcda5c4f354638838a905e8614d75493e12a67e80eaf0cf4725113bcc00a155b","source":{"kind":"arxiv","id":"1107.2462","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.2462","created_at":"2026-05-18T04:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"1107.2462v2","created_at":"2026-05-18T04:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.2462","created_at":"2026-05-18T04:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"3TNFYTZVIY4I","created_at":"2026-05-18T12:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"3TNFYTZVIY4IHCUQ","created_at":"2026-05-18T12:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"3TNFYTZV","created_at":"2026-05-18T12:26:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:3TNFYTZVIY4IHCUQL2DBJV2USP","target":"record","payload":{"canonical_record":{"source":{"id":"1107.2462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-07-13T04:28:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e5fcb0f4fe3a9602a20dea6a2209ea6d5bab1455b488603c5c7e9623748bf04","abstract_canon_sha256":"85b919c45b0ab255483f1e253e33aead4e71e530d9d85e57462b64c369e967e8"},"schema_version":"1.0"},"canonical_sha256":"dcda5c4f354638838a905e8614d75493e12a67e80eaf0cf4725113bcc00a155b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:08:34.601464Z","signature_b64":"vncAOHT9L5nntuHiANgFoflmGvZnfqYEkRdkmuIBH46T3GabVk1oXrOtPXDRHlRRlmbomo51RqdHxpG8xAvWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcda5c4f354638838a905e8614d75493e12a67e80eaf0cf4725113bcc00a155b","last_reissued_at":"2026-05-18T04:08:34.600985Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:08:34.600985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1107.2462","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":"2026-05-18T04:08:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8AOQmUcI3PpDcTKRawe+XUrnUKpKkZ1FokGvCRrYJjNsBsemJXoc/QSK3Eva31wS2WfI0AysccUatAf+6ICBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T16:18:09.245115Z"},"content_sha256":"6d490446aeb61d35bda141a3138eb0b1a5faed997a67cf867b5adb8407b042ec","schema_version":"1.0","event_id":"sha256:6d490446aeb61d35bda141a3138eb0b1a5faed997a67cf867b5adb8407b042ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:3TNFYTZVIY4IHCUQL2DBJV2USP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical Topic Models for Multi-Label Document Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"America Chambers, Mark Steyvers, Padhraic Smyth, Timothy N. Rubin","submitted_at":"2011-07-13T04:28:32Z","abstract_excerpt":"Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word token"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.2462","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":"2026-05-18T04:08:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFC2/fU7ssYDENEwH6SLq7EM23ZDmEq8UhUwq7obj3yRYRIejLO9yFAHjJGoQ58mMauxgHnkX2pfFcCAvGItBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T16:18:09.245480Z"},"content_sha256":"5a1c2ab3061acdf615d81439e9922d2e4a2abf6fb2d0465ac87feedf6e8787ca","schema_version":"1.0","event_id":"sha256:5a1c2ab3061acdf615d81439e9922d2e4a2abf6fb2d0465ac87feedf6e8787ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TNFYTZVIY4IHCUQL2DBJV2USP/bundle.json","state_url":"https://pith.science/pith/3TNFYTZVIY4IHCUQL2DBJV2USP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TNFYTZVIY4IHCUQL2DBJV2USP/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":"2026-06-28T16:18:09Z","links":{"resolver":"https://pith.science/pith/3TNFYTZVIY4IHCUQL2DBJV2USP","bundle":"https://pith.science/pith/3TNFYTZVIY4IHCUQL2DBJV2USP/bundle.json","state":"https://pith.science/pith/3TNFYTZVIY4IHCUQL2DBJV2USP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TNFYTZVIY4IHCUQL2DBJV2USP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:3TNFYTZVIY4IHCUQL2DBJV2USP","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":"85b919c45b0ab255483f1e253e33aead4e71e530d9d85e57462b64c369e967e8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-07-13T04:28:32Z","title_canon_sha256":"8e5fcb0f4fe3a9602a20dea6a2209ea6d5bab1455b488603c5c7e9623748bf04"},"schema_version":"1.0","source":{"id":"1107.2462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.2462","created_at":"2026-05-18T04:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"1107.2462v2","created_at":"2026-05-18T04:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.2462","created_at":"2026-05-18T04:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"3TNFYTZVIY4I","created_at":"2026-05-18T12:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"3TNFYTZVIY4IHCUQ","created_at":"2026-05-18T12:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"3TNFYTZV","created_at":"2026-05-18T12:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:5a1c2ab3061acdf615d81439e9922d2e4a2abf6fb2d0465ac87feedf6e8787ca","target":"graph","created_at":"2026-05-18T04:08:34Z","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":"Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This problem is amplified when the label frequencies exhibit the type of highly skewed distributions that are often observed in real-world datasets. In this paper we investigate a class of generative statistical topic models for multi-label documents that associate individual word token","authors_text":"America Chambers, Mark Steyvers, Padhraic Smyth, Timothy N. Rubin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-07-13T04:28:32Z","title":"Statistical Topic Models for Multi-Label Document Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.2462","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":"sha256:6d490446aeb61d35bda141a3138eb0b1a5faed997a67cf867b5adb8407b042ec","target":"record","created_at":"2026-05-18T04:08:34Z","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":"85b919c45b0ab255483f1e253e33aead4e71e530d9d85e57462b64c369e967e8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-07-13T04:28:32Z","title_canon_sha256":"8e5fcb0f4fe3a9602a20dea6a2209ea6d5bab1455b488603c5c7e9623748bf04"},"schema_version":"1.0","source":{"id":"1107.2462","kind":"arxiv","version":2}},"canonical_sha256":"dcda5c4f354638838a905e8614d75493e12a67e80eaf0cf4725113bcc00a155b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcda5c4f354638838a905e8614d75493e12a67e80eaf0cf4725113bcc00a155b","first_computed_at":"2026-05-18T04:08:34.600985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:08:34.600985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vncAOHT9L5nntuHiANgFoflmGvZnfqYEkRdkmuIBH46T3GabVk1oXrOtPXDRHlRRlmbomo51RqdHxpG8xAvWDA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:08:34.601464Z","signed_message":"canonical_sha256_bytes"},"source_id":"1107.2462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d490446aeb61d35bda141a3138eb0b1a5faed997a67cf867b5adb8407b042ec","sha256:5a1c2ab3061acdf615d81439e9922d2e4a2abf6fb2d0465ac87feedf6e8787ca"],"state_sha256":"c05e8658aa4b4589aef097a008df2069ce317514af2d365d3a73f56b228e6aad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Antmy+10LrbjAPamrdNJ+OPZd32b2jTJd5vXd3Yy3NIc6D+RzIFrXMxbLBSMy6gH4NcoBbNppl+iUyYyj7CiAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T16:18:09.247386Z","bundle_sha256":"6c926683c02a6ef381d24cebcff00ac45c0f62b2e51e17f87e6f5b0f8104e026"}}