{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4EIPXE4UPWJBXPAAM3XCGKLI25","short_pith_number":"pith:4EIPXE4U","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"},"canonical_sha256":"e110fb93947d921bbc0066ee232968d774c6e853a7a0fc6b5da78cdfd2aa5d78","source":{"kind":"arxiv","id":"2009.09672","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09672","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09672v2","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09672","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_12","alias_value":"4EIPXE4UPWJB","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_16","alias_value":"4EIPXE4UPWJBXPAA","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_8","alias_value":"4EIPXE4U","created_at":"2026-07-05T04:53:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4EIPXE4UPWJBXPAAM3XCGKLI25","target":"record","payload":{"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"},"canonical_sha256":"e110fb93947d921bbc0066ee232968d774c6e853a7a0fc6b5da78cdfd2aa5d78","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"},"source_kind":"arxiv","source_id":"2009.09672","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:53:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGz9RO5LtooDx8Jr87kH8mPYHDtFWl3SgwZ07ReaF/I/ByBwAuOXAtjHGnB/3AP5lbLg26qrlgHVNCFD5lNdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:55:14.298154Z"},"content_sha256":"ba9c18fa6327279878b36d520e70dde0974384c18ced55cf12cac202af579fe9","schema_version":"1.0","event_id":"sha256:ba9c18fa6327279878b36d520e70dde0974384c18ced55cf12cac202af579fe9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4EIPXE4UPWJBXPAAM3XCGKLI25","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:53:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKa3oS3Hh5ME1XJ+bKtjwiEDS/oH3FLKNLjjEYk/4KOSPqTG+Oqz+5K9VnS5Z2lIOR8kv4+Qmhe1Jc3oFZe4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:55:14.299040Z"},"content_sha256":"369016b97ad38661be32d7a25b7158efec1943dc215b9071f539a3e680de0ecb","schema_version":"1.0","event_id":"sha256:369016b97ad38661be32d7a25b7158efec1943dc215b9071f539a3e680de0ecb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/bundle.json","state_url":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T05:55:14Z","links":{"resolver":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25","bundle":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/bundle.json","state":"https://pith.science/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EIPXE4UPWJBXPAAM3XCGKLI25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4EIPXE4UPWJBXPAAM3XCGKLI25","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2d7a2d6bb0604caea4fcd1247d484a3eaf7ff11e4b4f3fff87e928874d8b22e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T08:14:30Z","title_canon_sha256":"c06906d205f9420929395f09845de63bf525b1bdf25d69bff5b2898b8c380275"},"schema_version":"1.0","source":{"id":"2009.09672","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09672","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09672v2","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09672","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_12","alias_value":"4EIPXE4UPWJB","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_16","alias_value":"4EIPXE4UPWJBXPAA","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_8","alias_value":"4EIPXE4U","created_at":"2026-07-05T04:53:23Z"}],"graph_snapshots":[{"event_id":"sha256:369016b97ad38661be32d7a25b7158efec1943dc215b9071f539a3e680de0ecb","target":"graph","created_at":"2026-07-05T04:53:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.09672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Jiajun Chen, Shujian Huang, Xin-Yu Dai, Zewei Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T08:14:30Z","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09672","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ba9c18fa6327279878b36d520e70dde0974384c18ced55cf12cac202af579fe9","target":"record","created_at":"2026-07-05T04:53:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2d7a2d6bb0604caea4fcd1247d484a3eaf7ff11e4b4f3fff87e928874d8b22e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T08:14:30Z","title_canon_sha256":"c06906d205f9420929395f09845de63bf525b1bdf25d69bff5b2898b8c380275"},"schema_version":"1.0","source":{"id":"2009.09672","kind":"arxiv","version":2}},"canonical_sha256":"e110fb93947d921bbc0066ee232968d774c6e853a7a0fc6b5da78cdfd2aa5d78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e110fb93947d921bbc0066ee232968d774c6e853a7a0fc6b5da78cdfd2aa5d78","first_computed_at":"2026-07-05T04:53:23.944270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:23.944270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xUdZqYIjNsI6EwEBwKb6YmT82YeROxA1NDoqfcVaFxi1S0r54wCetWvFosn2qzoP7+f0/wvstLmZ8HukgksvAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:23.944697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.09672","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba9c18fa6327279878b36d520e70dde0974384c18ced55cf12cac202af579fe9","sha256:369016b97ad38661be32d7a25b7158efec1943dc215b9071f539a3e680de0ecb"],"state_sha256":"2fae1532d1027da4c6a9fbeb0e966d7c14eb783aaeddf099eef0e8749d3c14e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGIBy4PB0Oc+JNNLOChHWgR4dD0tVk+SUyymn3ZUmHAltzhok+3g32NTeds9w7JJTuEBN+ORm8pQAWyBReGKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:55:14.384028Z","bundle_sha256":"a395df1c7959291bc352ebe8384c6de9a6bcb54954fabd26ad74bf36d6e71281"}}