{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3BTGCQ7OOLENNMZ4UJXY7NXHXQ","short_pith_number":"pith:3BTGCQ7O","schema_version":"1.0","canonical_sha256":"d8666143ee72c8d6b33ca26f8fb6e7bc14370692c2cdc5882eb9751b4c001b25","source":{"kind":"arxiv","id":"2106.12066","version":2},"attestation_state":"computed","paper":{"title":"It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexey Tikhonov, Max Ryabinin","submitted_at":"2021-06-22T21:25:43Z","abstract_excerpt":"Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English. Pretrained cross-lingual models are a source of powerful language-agnostic representations, yet their inherent reasoning capabilities are still actively studied. In this work, we design a simple approach to commonsense reasoning which trains a linear classifier with weights of multi-head attention as features. To evaluate this approach, we create a multilingual Winograd Schema corpus by processing several datasets f"},"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":"2106.12066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-22T21:25:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a2a5186ea293686b95a5159a73c27ab59b12378376a87067c1d301ce7262b403","abstract_canon_sha256":"7e3b27577af5461b392cd2a91d0f2dd1d27443f146ee745b716f0591dd5b09e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:38.527020Z","signature_b64":"psSprNxB6K8SwasDxuE40JQQLzVF0MzTgWKOCsNQGQ9mNgYNbgSWhZaq0N6H3xbYXlozvJv52iRVcCD2gJKtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8666143ee72c8d6b33ca26f8fb6e7bc14370692c2cdc5882eb9751b4c001b25","last_reissued_at":"2026-07-05T03:36:38.526566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:38.526566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexey Tikhonov, Max Ryabinin","submitted_at":"2021-06-22T21:25:43Z","abstract_excerpt":"Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English. Pretrained cross-lingual models are a source of powerful language-agnostic representations, yet their inherent reasoning capabilities are still actively studied. In this work, we design a simple approach to commonsense reasoning which trains a linear classifier with weights of multi-head attention as features. To evaluate this approach, we create a multilingual Winograd Schema corpus by processing several datasets f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12066","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/2106.12066/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":"2106.12066","created_at":"2026-07-05T03:36:38.526623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.12066v2","created_at":"2026-07-05T03:36:38.526623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12066","created_at":"2026-07-05T03:36:38.526623+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BTGCQ7OOLEN","created_at":"2026-07-05T03:36:38.526623+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BTGCQ7OOLENNMZ4","created_at":"2026-07-05T03:36:38.526623+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BTGCQ7O","created_at":"2026-07-05T03:36:38.526623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07501","citing_title":"Graph-of-Causal Evolution: Challenging Chain-of-Model for Reasoning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ","json":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ.json","graph_json":"https://pith.science/api/pith-number/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/graph.json","events_json":"https://pith.science/api/pith-number/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/events.json","paper":"https://pith.science/paper/3BTGCQ7O"},"agent_actions":{"view_html":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ","download_json":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ.json","view_paper":"https://pith.science/paper/3BTGCQ7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.12066&json=true","fetch_graph":"https://pith.science/api/pith-number/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/action/storage_attestation","attest_author":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/action/author_attestation","sign_citation":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/action/citation_signature","submit_replication":"https://pith.science/pith/3BTGCQ7OOLENNMZ4UJXY7NXHXQ/action/replication_record"}},"created_at":"2026-07-05T03:36:38.526623+00:00","updated_at":"2026-07-05T03:36:38.526623+00:00"}