{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4EIPXE4UPWJBXPAAM3XCGKLI25","short_pith_number":"pith:4EIPXE4U","schema_version":"1.0","canonical_sha256":"e110fb93947d921bbc0066ee232968d774c6e853a7a0fc6b5da78cdfd2aa5d78","source":{"kind":"arxiv","id":"2009.09672","version":2},"attestation_state":"computed","paper":{"title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Shujian Huang, Xin-Yu Dai, Zewei Sun","submitted_at":"2020-09-21T08:14:30Z","abstract_excerpt":"Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple masking method: HeadMask, in two specific ways. Experiments show that translation improvements are achieved on multiple language pairs. Subsequent empirical analyses also support our assumption and confirm the effectiveness of the method."},"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":"2009.09672","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T08:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"c06906d205f9420929395f09845de63bf525b1bdf25d69bff5b2898b8c380275","abstract_canon_sha256":"2d7a2d6bb0604caea4fcd1247d484a3eaf7ff11e4b4f3fff87e928874d8b22e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:23.944697Z","signature_b64":"xUdZqYIjNsI6EwEBwKb6YmT82YeROxA1NDoqfcVaFxi1S0r54wCetWvFosn2qzoP7+f0/wvstLmZ8HukgksvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e110fb93947d921bbc0066ee232968d774c6e853a7a0fc6b5da78cdfd2aa5d78","last_reissued_at":"2026-07-05T04:53:23.944270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:23.944270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Shujian Huang, Xin-Yu Dai, Zewei Sun","submitted_at":"2020-09-21T08:14:30Z","abstract_excerpt":"Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple masking method: HeadMask, in two specific ways. Experiments show that translation improvements are achieved on multiple language pairs. Subsequent empirical analyses also support our assumption and confirm the effectiveness of the method."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09672","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/2009.09672/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":"2009.09672","created_at":"2026-07-05T04:53:23.944333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09672v2","created_at":"2026-07-05T04:53:23.944333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09672","created_at":"2026-07-05T04:53:23.944333+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EIPXE4UPWJB","created_at":"2026-07-05T04:53:23.944333+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EIPXE4UPWJBXPAA","created_at":"2026-07-05T04:53:23.944333+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EIPXE4U","created_at":"2026-07-05T04:53:23.944333+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/4EIPXE4UPWJBXPAAM3XCGKLI25","json":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25.json","graph_json":"https://pith.science/api/pith-number/4EIPXE4UPWJBXPAAM3XCGKLI25/graph.json","events_json":"https://pith.science/api/pith-number/4EIPXE4UPWJBXPAAM3XCGKLI25/events.json","paper":"https://pith.science/paper/4EIPXE4U"},"agent_actions":{"view_html":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25","download_json":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25.json","view_paper":"https://pith.science/paper/4EIPXE4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09672&json=true","fetch_graph":"https://pith.science/api/pith-number/4EIPXE4UPWJBXPAAM3XCGKLI25/graph.json","fetch_events":"https://pith.science/api/pith-number/4EIPXE4UPWJBXPAAM3XCGKLI25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/action/storage_attestation","attest_author":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/action/author_attestation","sign_citation":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/action/citation_signature","submit_replication":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/action/replication_record"}},"created_at":"2026-07-05T04:53:23.944333+00:00","updated_at":"2026-07-05T04:53:23.944333+00:00"}