{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ITV4VLB3MIMLB264T7EQA7J4FY","short_pith_number":"pith:ITV4VLB3","canonical_record":{"source":{"id":"1905.09418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T01:13:24Z","cross_cats_sorted":[],"title_canon_sha256":"2db19ded3f1868d17795aa5c88183110f3268147151218aae2b2622d76035109","abstract_canon_sha256":"8182ce05840b7a58d9cec218aa4a9cc9be49170aa1db636ce8e4510046c5e4aa"},"schema_version":"1.0"},"canonical_sha256":"44ebcaac3b6218b0ebdc9fc9007d3c2e016503bb0be261eb21f01da36f321dd5","source":{"kind":"arxiv","id":"1905.09418","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09418","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09418v2","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09418","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"ITV4VLB3MIML","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"ITV4VLB3MIMLB264","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"ITV4VLB3","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ITV4VLB3MIMLB264T7EQA7J4FY","target":"record","payload":{"canonical_record":{"source":{"id":"1905.09418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T01:13:24Z","cross_cats_sorted":[],"title_canon_sha256":"2db19ded3f1868d17795aa5c88183110f3268147151218aae2b2622d76035109","abstract_canon_sha256":"8182ce05840b7a58d9cec218aa4a9cc9be49170aa1db636ce8e4510046c5e4aa"},"schema_version":"1.0"},"canonical_sha256":"44ebcaac3b6218b0ebdc9fc9007d3c2e016503bb0be261eb21f01da36f321dd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:56.044948Z","signature_b64":"PeKkZ1WI6yYRaD5SoBDBqxLLz18Du68rnzDW7LqSWs3a2SyqXJjbMSQOPi7EEFzbooa/nHG7nLe04aUc14boBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44ebcaac3b6218b0ebdc9fc9007d3c2e016503bb0be261eb21f01da36f321dd5","last_reissued_at":"2026-05-17T23:43:56.044278Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:56.044278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.09418","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":"2026-05-17T23:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7l47+R1ZimveAV/kTqbwU6uQEwEKtT29UEuH6C6TE7psfTLlAaf6ZJxlO/IntVdqYNQDdZxD7bgVM1pmYUtqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:46:16.120447Z"},"content_sha256":"c5756c23065fcfb66f9e0ecdd89aa2af66d114169926b5f259d43456d3a144b8","schema_version":"1.0","event_id":"sha256:c5756c23065fcfb66f9e0ecdd89aa2af66d114169926b5f259d43456d3a144b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ITV4VLB3MIMLB264T7EQA7J4FY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Talbot, Elena Voita, Fedor Moiseev, Ivan Titov, Rico Sennrich","submitted_at":"2019-05-23T01:13:24Z","abstract_excerpt":"Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance of the model and analyze the roles played by them. We find that the most important and confident heads play consistent and often linguistically-interpretable roles. When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, we observe that specialized heads are last to be pruned. Our novel pruning m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09418","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":""},"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":"2026-05-17T23:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"umm/c5gNDlAg0pOqHujZX4Hrnz0Rc0ZpTM6i578yQkv1YpeGRTT1NfxoPKvFxAk8o55g6wPznd5LbUsw3ou/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:46:16.120900Z"},"content_sha256":"a6126ecf5ca820847857131e7825eebe71f509818230d782dadd6c7fbfab5090","schema_version":"1.0","event_id":"sha256:a6126ecf5ca820847857131e7825eebe71f509818230d782dadd6c7fbfab5090"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ITV4VLB3MIMLB264T7EQA7J4FY/bundle.json","state_url":"https://pith.science/pith/ITV4VLB3MIMLB264T7EQA7J4FY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ITV4VLB3MIMLB264T7EQA7J4FY/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":"2026-05-30T07:46:16Z","links":{"resolver":"https://pith.science/pith/ITV4VLB3MIMLB264T7EQA7J4FY","bundle":"https://pith.science/pith/ITV4VLB3MIMLB264T7EQA7J4FY/bundle.json","state":"https://pith.science/pith/ITV4VLB3MIMLB264T7EQA7J4FY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ITV4VLB3MIMLB264T7EQA7J4FY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ITV4VLB3MIMLB264T7EQA7J4FY","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":"8182ce05840b7a58d9cec218aa4a9cc9be49170aa1db636ce8e4510046c5e4aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T01:13:24Z","title_canon_sha256":"2db19ded3f1868d17795aa5c88183110f3268147151218aae2b2622d76035109"},"schema_version":"1.0","source":{"id":"1905.09418","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09418","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09418v2","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09418","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"ITV4VLB3MIML","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"ITV4VLB3MIMLB264","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"ITV4VLB3","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:a6126ecf5ca820847857131e7825eebe71f509818230d782dadd6c7fbfab5090","target":"graph","created_at":"2026-05-17T23:43:56Z","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"},"paper":{"abstract_excerpt":"Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance of the model and analyze the roles played by them. We find that the most important and confident heads play consistent and often linguistically-interpretable roles. When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, we observe that specialized heads are last to be pruned. Our novel pruning m","authors_text":"David Talbot, Elena Voita, Fedor Moiseev, Ivan Titov, Rico Sennrich","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T01:13:24Z","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09418","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:c5756c23065fcfb66f9e0ecdd89aa2af66d114169926b5f259d43456d3a144b8","target":"record","created_at":"2026-05-17T23:43:56Z","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":"8182ce05840b7a58d9cec218aa4a9cc9be49170aa1db636ce8e4510046c5e4aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T01:13:24Z","title_canon_sha256":"2db19ded3f1868d17795aa5c88183110f3268147151218aae2b2622d76035109"},"schema_version":"1.0","source":{"id":"1905.09418","kind":"arxiv","version":2}},"canonical_sha256":"44ebcaac3b6218b0ebdc9fc9007d3c2e016503bb0be261eb21f01da36f321dd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44ebcaac3b6218b0ebdc9fc9007d3c2e016503bb0be261eb21f01da36f321dd5","first_computed_at":"2026-05-17T23:43:56.044278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:56.044278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PeKkZ1WI6yYRaD5SoBDBqxLLz18Du68rnzDW7LqSWs3a2SyqXJjbMSQOPi7EEFzbooa/nHG7nLe04aUc14boBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:56.044948Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09418","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5756c23065fcfb66f9e0ecdd89aa2af66d114169926b5f259d43456d3a144b8","sha256:a6126ecf5ca820847857131e7825eebe71f509818230d782dadd6c7fbfab5090"],"state_sha256":"6cc6f2c7fb3d5fd86670808d8885f2a011afb17b3603afd6dececce92ee1d76a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1ayMu3msuyOW8+16IYBQriBg+KxvVTvHh2D3sQh648PyKTQFIMkiQc/iAYKqoB3hFj4tPWtJSe5E+/N3JqjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:46:16.123358Z","bundle_sha256":"a675f36decb9964ce0cb7d51434175843ae3562b7b4c069e43666f1edb59f6cd"}}