{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P6FWJFHEXHJFWKAE2KJ25LKNIL","short_pith_number":"pith:P6FWJFHE","canonical_record":{"source":{"id":"2106.09650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T16:53:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"61bd4869abd1ce766f2e519c6da9e809cd7532684fd91e81f2a6c6f6d85a3229","abstract_canon_sha256":"cc1e5315c5ea89c0110a6320e6343dd36b55420ee7bce0d2922c84596a134d85"},"schema_version":"1.0"},"canonical_sha256":"7f8b6494e4b9d25b2804d293aead4d42c6f5cd5cca4858d0fd4d9881b0660c3c","source":{"kind":"arxiv","id":"2106.09650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09650","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09650v1","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09650","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"P6FWJFHEXHJF","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"P6FWJFHEXHJFWKAE","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"P6FWJFHE","created_at":"2026-07-05T02:50:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P6FWJFHEXHJFWKAE2KJ25LKNIL","target":"record","payload":{"canonical_record":{"source":{"id":"2106.09650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T16:53:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"61bd4869abd1ce766f2e519c6da9e809cd7532684fd91e81f2a6c6f6d85a3229","abstract_canon_sha256":"cc1e5315c5ea89c0110a6320e6343dd36b55420ee7bce0d2922c84596a134d85"},"schema_version":"1.0"},"canonical_sha256":"7f8b6494e4b9d25b2804d293aead4d42c6f5cd5cca4858d0fd4d9881b0660c3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:18.280508Z","signature_b64":"kIdFRHBlNzYKwk92p+AO9QFqVsujyd6eDQ0PwsrfmDHGGQdRdJwNlm6GepxmSKE5rnvGSTVeYOabWi2I1YxEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f8b6494e4b9d25b2804d293aead4d42c6f5cd5cca4858d0fd4d9881b0660c3c","last_reissued_at":"2026-07-05T02:50:18.279954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:18.279954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.09650","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z+ZkELhuoFuceet7BVXgalnM7kUhThbZpAkjU7xngzKyd7WyIflS/gCpmKY7VWRMw9R6MZ95kfKJRegnJqCpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:12:25.852203Z"},"content_sha256":"fb750723fcf456e2cf29486a1213a17aab738a25878336c0baa85be8c813407c","schema_version":"1.0","event_id":"sha256:fb750723fcf456e2cf29486a1213a17aab738a25878336c0baa85be8c813407c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P6FWJFHEXHJFWKAE2KJ25LKNIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jialu Liu, Jiawei Han, Liyuan Liu","submitted_at":"2021-06-17T16:53:22Z","abstract_excerpt":"Multi-head attention plays a crucial role in the recent success of Transformer models, which leads to consistent performance improvements over conventional attention in various applications. The popular belief is that this effectiveness stems from the ability of jointly attending multiple positions. In this paper, we first demonstrate that jointly attending multiple positions is not a unique feature of multi-head attention, as multi-layer single-head attention also attends multiple positions and is more effective. Then, we suggest the main advantage of the multi-head attention is the training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09650","kind":"arxiv","version":1},"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/2106.09650/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":"2026-07-05T02:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSQGSc9SzdR6Tky30dpDSs5++s7cKyszb+sSQoCP3CEOWhPfYsEEjFEkMDJhcwMcZLbzi8rSF0v821Y1IIqWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:12:25.852903Z"},"content_sha256":"d4ccc2f9327afa619f660daada064017c43c3e069438d2f67c2d13e82c549b4d","schema_version":"1.0","event_id":"sha256:d4ccc2f9327afa619f660daada064017c43c3e069438d2f67c2d13e82c549b4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL/bundle.json","state_url":"https://pith.science/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL/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":"2026-08-13T13:12:25Z","links":{"resolver":"https://pith.science/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL","bundle":"https://pith.science/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL/bundle.json","state":"https://pith.science/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6FWJFHEXHJFWKAE2KJ25LKNIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P6FWJFHEXHJFWKAE2KJ25LKNIL","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":"cc1e5315c5ea89c0110a6320e6343dd36b55420ee7bce0d2922c84596a134d85","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T16:53:22Z","title_canon_sha256":"61bd4869abd1ce766f2e519c6da9e809cd7532684fd91e81f2a6c6f6d85a3229"},"schema_version":"1.0","source":{"id":"2106.09650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09650","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09650v1","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09650","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"P6FWJFHEXHJF","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"P6FWJFHEXHJFWKAE","created_at":"2026-07-05T02:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"P6FWJFHE","created_at":"2026-07-05T02:50:18Z"}],"graph_snapshots":[{"event_id":"sha256:d4ccc2f9327afa619f660daada064017c43c3e069438d2f67c2d13e82c549b4d","target":"graph","created_at":"2026-07-05T02:50:18Z","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/2106.09650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-head attention plays a crucial role in the recent success of Transformer models, which leads to consistent performance improvements over conventional attention in various applications. The popular belief is that this effectiveness stems from the ability of jointly attending multiple positions. In this paper, we first demonstrate that jointly attending multiple positions is not a unique feature of multi-head attention, as multi-layer single-head attention also attends multiple positions and is more effective. Then, we suggest the main advantage of the multi-head attention is the training ","authors_text":"Jialu Liu, Jiawei Han, Liyuan Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T16:53:22Z","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09650","kind":"arxiv","version":1},"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:fb750723fcf456e2cf29486a1213a17aab738a25878336c0baa85be8c813407c","target":"record","created_at":"2026-07-05T02:50:18Z","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":"cc1e5315c5ea89c0110a6320e6343dd36b55420ee7bce0d2922c84596a134d85","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T16:53:22Z","title_canon_sha256":"61bd4869abd1ce766f2e519c6da9e809cd7532684fd91e81f2a6c6f6d85a3229"},"schema_version":"1.0","source":{"id":"2106.09650","kind":"arxiv","version":1}},"canonical_sha256":"7f8b6494e4b9d25b2804d293aead4d42c6f5cd5cca4858d0fd4d9881b0660c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f8b6494e4b9d25b2804d293aead4d42c6f5cd5cca4858d0fd4d9881b0660c3c","first_computed_at":"2026-07-05T02:50:18.279954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:18.279954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kIdFRHBlNzYKwk92p+AO9QFqVsujyd6eDQ0PwsrfmDHGGQdRdJwNlm6GepxmSKE5rnvGSTVeYOabWi2I1YxEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:18.280508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb750723fcf456e2cf29486a1213a17aab738a25878336c0baa85be8c813407c","sha256:d4ccc2f9327afa619f660daada064017c43c3e069438d2f67c2d13e82c549b4d"],"state_sha256":"cde5f716f3975200cb4bda7f763322f4e80b0ddf67878687b3520c73d559cab7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3RP+yhZiEa1StPHahQLGyp5U29ySqciFhvPlbi5nZ+C8qJjQA4qI0JECb+fokdTdyYs3uQ0JFhjIuJL5uB6QDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:12:25.858660Z","bundle_sha256":"7577c6ef5bac41fd15fc97fb18343c32acec9ace6b0a73954808b3ec8dcec7a7"}}