{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7FZQQ6HPZKBD24KQCLC3F3L273","short_pith_number":"pith:7FZQQ6HP","schema_version":"1.0","canonical_sha256":"f9730878efca823d715012c5b2ed7afeeac299fbcfdca578d0237eff1a157c8c","source":{"kind":"arxiv","id":"2507.03761","version":1},"attestation_state":"computed","paper":{"title":"Ranking-based Fusion Algorithms for Extreme Multi-label Text Classification (XMTC)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Celso Fran\\c{c}a, Gestefane Rabbi, Leonardo Rocha, Marcos Andr\\'e Gon\\c{c}alves, Thiago Salles, Washington Cunha","submitted_at":"2025-07-04T18:17:52Z","abstract_excerpt":"In the context of Extreme Multi-label Text Classification (XMTC), where labels are assigned to text instances from a large label space, the long-tail distribution of labels presents a significant challenge. Labels can be broadly categorized into frequent, high-coverage \\textbf{head labels} and infrequent, low-coverage \\textbf{tail labels}, complicating the task of balancing effectiveness across all labels. To address this, combining predictions from multiple retrieval methods, such as sparse retrievers (e.g., BM25) and dense retrievers (e.g., fine-tuned BERT), offers a promising solution. The "},"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":"2507.03761","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-04T18:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"37647e133df5fba9700c9a758c5a48e03b922aee8d7f505b21c0b00dfb331e36","abstract_canon_sha256":"3191930c9a8c2fb99edde32218383959cedbbd9f2ab1a35d3d558e2fcb3cfc5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:04.687415Z","signature_b64":"KAQjin10UoRw8H+cuuLCFlx3Z5SrmTXCAeCPtONjQjfYPNR1Tnt/jzKRC148a0k0i7NtDbx66F2beQjMaZWdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9730878efca823d715012c5b2ed7afeeac299fbcfdca578d0237eff1a157c8c","last_reissued_at":"2026-07-05T11:32:04.686919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:04.686919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ranking-based Fusion Algorithms for Extreme Multi-label Text Classification (XMTC)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Celso Fran\\c{c}a, Gestefane Rabbi, Leonardo Rocha, Marcos Andr\\'e Gon\\c{c}alves, Thiago Salles, Washington Cunha","submitted_at":"2025-07-04T18:17:52Z","abstract_excerpt":"In the context of Extreme Multi-label Text Classification (XMTC), where labels are assigned to text instances from a large label space, the long-tail distribution of labels presents a significant challenge. Labels can be broadly categorized into frequent, high-coverage \\textbf{head labels} and infrequent, low-coverage \\textbf{tail labels}, complicating the task of balancing effectiveness across all labels. To address this, combining predictions from multiple retrieval methods, such as sparse retrievers (e.g., BM25) and dense retrievers (e.g., fine-tuned BERT), offers a promising solution. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03761","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/2507.03761/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":"2507.03761","created_at":"2026-07-05T11:32:04.686979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03761v1","created_at":"2026-07-05T11:32:04.686979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03761","created_at":"2026-07-05T11:32:04.686979+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FZQQ6HPZKBD","created_at":"2026-07-05T11:32:04.686979+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FZQQ6HPZKBD24KQ","created_at":"2026-07-05T11:32:04.686979+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FZQQ6HP","created_at":"2026-07-05T11:32:04.686979+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/7FZQQ6HPZKBD24KQCLC3F3L273","json":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273.json","graph_json":"https://pith.science/api/pith-number/7FZQQ6HPZKBD24KQCLC3F3L273/graph.json","events_json":"https://pith.science/api/pith-number/7FZQQ6HPZKBD24KQCLC3F3L273/events.json","paper":"https://pith.science/paper/7FZQQ6HP"},"agent_actions":{"view_html":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273","download_json":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273.json","view_paper":"https://pith.science/paper/7FZQQ6HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03761&json=true","fetch_graph":"https://pith.science/api/pith-number/7FZQQ6HPZKBD24KQCLC3F3L273/graph.json","fetch_events":"https://pith.science/api/pith-number/7FZQQ6HPZKBD24KQCLC3F3L273/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273/action/storage_attestation","attest_author":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273/action/author_attestation","sign_citation":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273/action/citation_signature","submit_replication":"https://pith.science/pith/7FZQQ6HPZKBD24KQCLC3F3L273/action/replication_record"}},"created_at":"2026-07-05T11:32:04.686979+00:00","updated_at":"2026-07-05T11:32:04.686979+00:00"}