{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QJZIINCKVRJ2QGKVQOJ5U2ZGLA","short_pith_number":"pith:QJZIINCK","schema_version":"1.0","canonical_sha256":"827284344aac53a819558393da6b265811e088c438de5a4acffbd8bff742c45c","source":{"kind":"arxiv","id":"2102.12227","version":3},"attestation_state":"computed","paper":{"title":"Multi-Task Attentive Residual Networks for Argument Mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrea Galassi, Marco Lippi, Paolo Torroni","submitted_at":"2021-02-24T11:35:28Z","abstract_excerpt":"We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesti"},"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":"2102.12227","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T11:35:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ebe9d691e6156c0d4255346a657873afed2d95184cdb230564e10be2b591ffa2","abstract_canon_sha256":"62e7fa24dbe019fd39ef5513bd0cdf96bb3d97b6fc44a21f84ee682fc13f16f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:02.162932Z","signature_b64":"iuF7jCsQJNxKyF6pvo6vLSQeclTzrlCVwK2KyZ8hZkg6puwzbkDLMyeesdhdqoi50IVqz9XzcjLUSXDlIRIwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827284344aac53a819558393da6b265811e088c438de5a4acffbd8bff742c45c","last_reissued_at":"2026-07-05T06:14:02.162534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:02.162534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Attentive Residual Networks for Argument Mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrea Galassi, Marco Lippi, Paolo Torroni","submitted_at":"2021-02-24T11:35:28Z","abstract_excerpt":"We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12227","kind":"arxiv","version":3},"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/2102.12227/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":"2102.12227","created_at":"2026-07-05T06:14:02.162587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.12227v3","created_at":"2026-07-05T06:14:02.162587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12227","created_at":"2026-07-05T06:14:02.162587+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJZIINCKVRJ2","created_at":"2026-07-05T06:14:02.162587+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJZIINCKVRJ2QGKV","created_at":"2026-07-05T06:14:02.162587+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJZIINCK","created_at":"2026-07-05T06:14:02.162587+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/QJZIINCKVRJ2QGKVQOJ5U2ZGLA","json":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA.json","graph_json":"https://pith.science/api/pith-number/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/graph.json","events_json":"https://pith.science/api/pith-number/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/events.json","paper":"https://pith.science/paper/QJZIINCK"},"agent_actions":{"view_html":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA","download_json":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA.json","view_paper":"https://pith.science/paper/QJZIINCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.12227&json=true","fetch_graph":"https://pith.science/api/pith-number/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/graph.json","fetch_events":"https://pith.science/api/pith-number/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/action/storage_attestation","attest_author":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/action/author_attestation","sign_citation":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/action/citation_signature","submit_replication":"https://pith.science/pith/QJZIINCKVRJ2QGKVQOJ5U2ZGLA/action/replication_record"}},"created_at":"2026-07-05T06:14:02.162587+00:00","updated_at":"2026-07-05T06:14:02.162587+00:00"}