{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QIWFTLLOXNQUJUZHQHDWJIOYF5","short_pith_number":"pith:QIWFTLLO","canonical_record":{"source":{"id":"2007.02439","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-05T20:19:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"89333645c1223784f8b5807c1dcca2ba03d79a753d87ff6c9b06d06e74ce1270","abstract_canon_sha256":"2f420dc9d7db97b029d5b73e121d4c3f3d06e09453aa0f5cff5bb6b98c6103ed"},"schema_version":"1.0"},"canonical_sha256":"822c59ad6ebb6144d32781c764a1d82f54e93d44709aa81d2995bd63779ef176","source":{"kind":"arxiv","id":"2007.02439","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02439","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02439v2","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02439","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"QIWFTLLOXNQU","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"QIWFTLLOXNQUJUZH","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"QIWFTLLO","created_at":"2026-07-05T01:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QIWFTLLOXNQUJUZHQHDWJIOYF5","target":"record","payload":{"canonical_record":{"source":{"id":"2007.02439","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-05T20:19:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"89333645c1223784f8b5807c1dcca2ba03d79a753d87ff6c9b06d06e74ce1270","abstract_canon_sha256":"2f420dc9d7db97b029d5b73e121d4c3f3d06e09453aa0f5cff5bb6b98c6103ed"},"schema_version":"1.0"},"canonical_sha256":"822c59ad6ebb6144d32781c764a1d82f54e93d44709aa81d2995bd63779ef176","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:25.235214Z","signature_b64":"9Um0cwj42NlGzdPuGNmFr4KCmyyOPPG5dG6PeTlLvDkEqKKfdOFN6IxjKK/+nKqTPWy3fh13hQb/QKG/aAHHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"822c59ad6ebb6144d32781c764a1d82f54e93d44709aa81d2995bd63779ef176","last_reissued_at":"2026-07-05T01:27:25.234759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:25.234759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.02439","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":"2026-07-05T01:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxzC3PqKqJX6qYO293EfYNQB7H4PtqKIJ5LbwaZt5Jb+YsHpmFb3REaUTzQQCk6e23uHiOwYYz1jF2gFqfsaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:46:18.332870Z"},"content_sha256":"b9e48bb1a73072527edd89ba5c34fd6982c512051c12fc263b581b3e6d03efa4","schema_version":"1.0","event_id":"sha256:b9e48bb1a73072527edd89ba5c34fd6982c512051c12fc263b581b3e6d03efa4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QIWFTLLOXNQUJUZHQHDWJIOYF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brian D. Davison, Da-Han Wang, Hui Ye, Zhiyu Chen","submitted_at":"2020-07-05T20:19:29Z","abstract_excerpt":"Extreme multi-label text classification (XMTC) is a task for tagging a given text with the most relevant labels from an extremely large label set. We propose a novel deep learning method called APLC-XLNet. Our approach fine-tunes the recently released generalized autoregressive pretrained model (XLNet) to learn a dense representation for the input text. We propose Adaptive Probabilistic Label Clusters (APLC) to approximate the cross entropy loss by exploiting the unbalanced label distribution to form clusters that explicitly reduce the computational time. Our experiments, carried out on five b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02439","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.02439/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGpc9dMVY+63BR6igYGNYRd5u4XtT3HkkRgVv6Cl6+1Mh8nqbjp4yn3ZkxMkjO9P9l62Dygb3vMNtMHAARi8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:46:18.333494Z"},"content_sha256":"d502ccd52c7c71dccc9b24e5552c9f6927dba1d21fd779eb01dc8a8f507a8c1e","schema_version":"1.0","event_id":"sha256:d502ccd52c7c71dccc9b24e5552c9f6927dba1d21fd779eb01dc8a8f507a8c1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5/bundle.json","state_url":"https://pith.science/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5/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":"2026-08-19T16:46:18Z","links":{"resolver":"https://pith.science/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5","bundle":"https://pith.science/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5/bundle.json","state":"https://pith.science/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIWFTLLOXNQUJUZHQHDWJIOYF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QIWFTLLOXNQUJUZHQHDWJIOYF5","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":"2f420dc9d7db97b029d5b73e121d4c3f3d06e09453aa0f5cff5bb6b98c6103ed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-05T20:19:29Z","title_canon_sha256":"89333645c1223784f8b5807c1dcca2ba03d79a753d87ff6c9b06d06e74ce1270"},"schema_version":"1.0","source":{"id":"2007.02439","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02439","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02439v2","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02439","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"QIWFTLLOXNQU","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"QIWFTLLOXNQUJUZH","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"QIWFTLLO","created_at":"2026-07-05T01:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:d502ccd52c7c71dccc9b24e5552c9f6927dba1d21fd779eb01dc8a8f507a8c1e","target":"graph","created_at":"2026-07-05T01:27:25Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.02439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extreme multi-label text classification (XMTC) is a task for tagging a given text with the most relevant labels from an extremely large label set. We propose a novel deep learning method called APLC-XLNet. Our approach fine-tunes the recently released generalized autoregressive pretrained model (XLNet) to learn a dense representation for the input text. We propose Adaptive Probabilistic Label Clusters (APLC) to approximate the cross entropy loss by exploiting the unbalanced label distribution to form clusters that explicitly reduce the computational time. Our experiments, carried out on five b","authors_text":"Brian D. Davison, Da-Han Wang, Hui Ye, Zhiyu Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-05T20:19:29Z","title":"Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02439","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:b9e48bb1a73072527edd89ba5c34fd6982c512051c12fc263b581b3e6d03efa4","target":"record","created_at":"2026-07-05T01:27:25Z","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":"2f420dc9d7db97b029d5b73e121d4c3f3d06e09453aa0f5cff5bb6b98c6103ed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-05T20:19:29Z","title_canon_sha256":"89333645c1223784f8b5807c1dcca2ba03d79a753d87ff6c9b06d06e74ce1270"},"schema_version":"1.0","source":{"id":"2007.02439","kind":"arxiv","version":2}},"canonical_sha256":"822c59ad6ebb6144d32781c764a1d82f54e93d44709aa81d2995bd63779ef176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"822c59ad6ebb6144d32781c764a1d82f54e93d44709aa81d2995bd63779ef176","first_computed_at":"2026-07-05T01:27:25.234759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:25.234759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Um0cwj42NlGzdPuGNmFr4KCmyyOPPG5dG6PeTlLvDkEqKKfdOFN6IxjKK/+nKqTPWy3fh13hQb/QKG/aAHHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:25.235214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.02439","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9e48bb1a73072527edd89ba5c34fd6982c512051c12fc263b581b3e6d03efa4","sha256:d502ccd52c7c71dccc9b24e5552c9f6927dba1d21fd779eb01dc8a8f507a8c1e"],"state_sha256":"727ae6602482f27aa0c3b3090100a3237a7277a55c270bd80b2ca5d93c02b6d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NrsHk8189AbJFD4oU4nsKjlhcKb3Ok0FKUej2nz/OFMBc1tcxLN9RGa6VG9Ko94ipcWw/fkRVvcvzYEKTsFbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:46:18.340051Z","bundle_sha256":"fb0a0fd98358b2f01f515b974b5cebef5ec9b401e30e7f76edd4d8204cf6dbbf"}}