{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5BQN6DCJPHRUJSIRA4IKQ5Q3JI","short_pith_number":"pith:5BQN6DCJ","schema_version":"1.0","canonical_sha256":"e860df0c4979e344c9110710a8761b4a318673756c6af7c110eee529cd50a1f8","source":{"kind":"arxiv","id":"2305.05627","version":1},"attestation_state":"computed","paper":{"title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis, Yova Kementchedjhieva","submitted_at":"2023-05-09T17:13:53Z","abstract_excerpt":"Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. We carry out experiments on four datasets -- two in the legal domain and two in the biomedical domain, each with two levels of label granularity -- and always depart from the same pre-trained model, T5. Our results show that encoder-decoder methods outperform en"},"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":"2305.05627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:13:53Z","cross_cats_sorted":[],"title_canon_sha256":"32a6fb2b68eea1bbbf812332a0dc59bff30522fd825d7d360f97499869b829d9","abstract_canon_sha256":"0bae9924310b43db7a77b1b794670a8f3dcc0a56275eccb66f4dd982419f8774"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:37.143326Z","signature_b64":"QT60cbwUMYEvK0lkhrOR2WZBG9GW8QuHB9wNqVhAAgwnZCnVvkChuKqYeLnmMyuBHg9K1D+zpDZGcDDBCJKjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e860df0c4979e344c9110710a8761b4a318673756c6af7c110eee529cd50a1f8","last_reissued_at":"2026-07-05T06:08:37.142834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:37.142834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis, Yova Kementchedjhieva","submitted_at":"2023-05-09T17:13:53Z","abstract_excerpt":"Standard methods for multi-label text classification largely rely on encoder-only pre-trained language models, whereas encoder-decoder models have proven more effective in other classification tasks. In this study, we compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. We carry out experiments on four datasets -- two in the legal domain and two in the biomedical domain, each with two levels of label granularity -- and always depart from the same pre-trained model, T5. Our results show that encoder-decoder methods outperform en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05627","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/2305.05627/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":"2305.05627","created_at":"2026-07-05T06:08:37.142899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05627v1","created_at":"2026-07-05T06:08:37.142899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05627","created_at":"2026-07-05T06:08:37.142899+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BQN6DCJPHRU","created_at":"2026-07-05T06:08:37.142899+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BQN6DCJPHRUJSIR","created_at":"2026-07-05T06:08:37.142899+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BQN6DCJ","created_at":"2026-07-05T06:08:37.142899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.14565","citing_title":"Detecting and Characterising Mobile App Metamorphosis in Google Play Store","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI","json":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI.json","graph_json":"https://pith.science/api/pith-number/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/graph.json","events_json":"https://pith.science/api/pith-number/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/events.json","paper":"https://pith.science/paper/5BQN6DCJ"},"agent_actions":{"view_html":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI","download_json":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI.json","view_paper":"https://pith.science/paper/5BQN6DCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05627&json=true","fetch_graph":"https://pith.science/api/pith-number/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/graph.json","fetch_events":"https://pith.science/api/pith-number/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/action/storage_attestation","attest_author":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/action/author_attestation","sign_citation":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/action/citation_signature","submit_replication":"https://pith.science/pith/5BQN6DCJPHRUJSIRA4IKQ5Q3JI/action/replication_record"}},"created_at":"2026-07-05T06:08:37.142899+00:00","updated_at":"2026-07-05T06:08:37.142899+00:00"}