{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OKFVFFAJON7EPHSYGFSDEYLQIR","short_pith_number":"pith:OKFVFFAJ","schema_version":"1.0","canonical_sha256":"728b529409737e479e58316432617044701aa9f488a51ebf8b38d61112d8c9f1","source":{"kind":"arxiv","id":"2204.00933","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Local and Global Features in Transformer-based Extreme Multi-label Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Likun Lei, Ruohong Zhang, Tom Vu, Yau-Shian Wang, Yiming Yang","submitted_at":"2022-04-02T19:55:23Z","abstract_excerpt":"Extreme multi-label text classification (XMTC) is the task of tagging each document with the relevant labels from a very large space of predefined categories. Recently, large pre-trained Transformer models have made significant performance improvements in XMTC, which typically use the embedding of the special CLS token to represent the entire document semantics as a global feature vector, and match it against candidate labels. However, we argue that such a global feature vector may not be sufficient to represent different granularity levels of semantics in the document, and that complementing "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.00933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-02T19:55:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d42e1daebc67769212d1d42fcbcdb8734d096619236b5ac6d2358de3c7f89697","abstract_canon_sha256":"a76a6cae1e7ebab9d9ea92475fb71f368ffa6ad5f3265813c2722e21abd905f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:58.475666Z","signature_b64":"CS0QU8jxxXDpVLjym+zgE1d7OOpGnKuX1D3WQ6Lv7+lTwUEAz8KZZ7mkIVC0G508uNkFmNpqtoDAi8Sy0fDmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"728b529409737e479e58316432617044701aa9f488a51ebf8b38d61112d8c9f1","last_reissued_at":"2026-07-05T04:10:58.475271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:58.475271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Local and Global Features in Transformer-based Extreme Multi-label Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Likun Lei, Ruohong Zhang, Tom Vu, Yau-Shian Wang, Yiming Yang","submitted_at":"2022-04-02T19:55:23Z","abstract_excerpt":"Extreme multi-label text classification (XMTC) is the task of tagging each document with the relevant labels from a very large space of predefined categories. Recently, large pre-trained Transformer models have made significant performance improvements in XMTC, which typically use the embedding of the special CLS token to represent the entire document semantics as a global feature vector, and match it against candidate labels. However, we argue that such a global feature vector may not be sufficient to represent different granularity levels of semantics in the document, and that complementing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00933","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.00933/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.00933","created_at":"2026-07-05T04:10:58.475325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00933v1","created_at":"2026-07-05T04:10:58.475325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00933","created_at":"2026-07-05T04:10:58.475325+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKFVFFAJON7E","created_at":"2026-07-05T04:10:58.475325+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKFVFFAJON7EPHSY","created_at":"2026-07-05T04:10:58.475325+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKFVFFAJ","created_at":"2026-07-05T04:10:58.475325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR","json":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR.json","graph_json":"https://pith.science/api/pith-number/OKFVFFAJON7EPHSYGFSDEYLQIR/graph.json","events_json":"https://pith.science/api/pith-number/OKFVFFAJON7EPHSYGFSDEYLQIR/events.json","paper":"https://pith.science/paper/OKFVFFAJ"},"agent_actions":{"view_html":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR","download_json":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR.json","view_paper":"https://pith.science/paper/OKFVFFAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00933&json=true","fetch_graph":"https://pith.science/api/pith-number/OKFVFFAJON7EPHSYGFSDEYLQIR/graph.json","fetch_events":"https://pith.science/api/pith-number/OKFVFFAJON7EPHSYGFSDEYLQIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR/action/storage_attestation","attest_author":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR/action/author_attestation","sign_citation":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR/action/citation_signature","submit_replication":"https://pith.science/pith/OKFVFFAJON7EPHSYGFSDEYLQIR/action/replication_record"}},"created_at":"2026-07-05T04:10:58.475325+00:00","updated_at":"2026-07-05T04:10:58.475325+00:00"}