{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:D7VLL33GC2OJ7PF4XEGGSEKR3X","short_pith_number":"pith:D7VLL33G","canonical_record":{"source":{"id":"2003.02436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-05T05:17:17Z","cross_cats_sorted":["cs.NE","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"75b956b0d3615c1a96bf265ba58d92b153d30a07fb95f2907f6db0fb3b41442b","abstract_canon_sha256":"80d1c337000830737848a4391c6f4defa1a2387f68cbde76fd72cf3ad2a69d71"},"schema_version":"1.0"},"canonical_sha256":"1feab5ef66169c9fbcbcb90c691151ddf57eca52217880c1041ef6ea3da16eb6","source":{"kind":"arxiv","id":"2003.02436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02436","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02436v1","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02436","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"D7VLL33GC2OJ","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"pith_short_16","alias_value":"D7VLL33GC2OJ7PF4","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"pith_short_8","alias_value":"D7VLL33G","created_at":"2026-07-05T00:45:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:D7VLL33GC2OJ7PF4XEGGSEKR3X","target":"record","payload":{"canonical_record":{"source":{"id":"2003.02436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-05T05:17:17Z","cross_cats_sorted":["cs.NE","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"75b956b0d3615c1a96bf265ba58d92b153d30a07fb95f2907f6db0fb3b41442b","abstract_canon_sha256":"80d1c337000830737848a4391c6f4defa1a2387f68cbde76fd72cf3ad2a69d71"},"schema_version":"1.0"},"canonical_sha256":"1feab5ef66169c9fbcbcb90c691151ddf57eca52217880c1041ef6ea3da16eb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:56.499168Z","signature_b64":"FtPqzy5QH0pHKZ0zF0zSu/RRApv21IY6gpLGyxVlmG56YBQSPu70IVUwu2pkC3a0GUuxVEUfITtGRGYGfaDICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1feab5ef66169c9fbcbcb90c691151ddf57eca52217880c1041ef6ea3da16eb6","last_reissued_at":"2026-07-05T00:45:56.498692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:56.498692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.02436","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":"2026-07-05T00:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GbtOhfnOFfI1wjN1NskGnT9bbSksv/mEWrtERK9pt9lVe+lCE811sQxFXwq1sJqQHmNDJkiU81bLAq17wcOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T04:07:57.484016Z"},"content_sha256":"c2ec5634d2a6c0249ded2938687ec95845a76d246108f9e74747e2e08a7610f6","schema_version":"1.0","event_id":"sha256:c2ec5634d2a6c0249ded2938687ec95845a76d246108f9e74747e2e08a7610f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:D7VLL33GC2OJ7PF4XEGGSEKR3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Talking-Heads Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Le Hou, Nan Ding, Noam Shazeer, Youlong Cheng, Zhenzhong Lan","submitted_at":"2020-03-05T05:17:17Z","abstract_excerpt":"We introduce \"talking-heads attention\" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02436","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/2003.02436/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":"2026-07-05T00:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U2Hb5rUmcaW4Wx2lXC8whObOcGUMXx9ajYwKbez79yd9jsaALU+9q4rb1wSMV7fDlPEDU3MOggTkO7ijQFOxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T04:07:57.484403Z"},"content_sha256":"2bdea7982487235ff6a1f1cd74a5e8ba862514f3216e58f106277317c3b2003a","schema_version":"1.0","event_id":"sha256:2bdea7982487235ff6a1f1cd74a5e8ba862514f3216e58f106277317c3b2003a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X/bundle.json","state_url":"https://pith.science/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X/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":"2026-07-17T04:07:57Z","links":{"resolver":"https://pith.science/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X","bundle":"https://pith.science/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X/bundle.json","state":"https://pith.science/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7VLL33GC2OJ7PF4XEGGSEKR3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:D7VLL33GC2OJ7PF4XEGGSEKR3X","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":"80d1c337000830737848a4391c6f4defa1a2387f68cbde76fd72cf3ad2a69d71","cross_cats_sorted":["cs.NE","cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-05T05:17:17Z","title_canon_sha256":"75b956b0d3615c1a96bf265ba58d92b153d30a07fb95f2907f6db0fb3b41442b"},"schema_version":"1.0","source":{"id":"2003.02436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02436","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02436v1","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02436","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"D7VLL33GC2OJ","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"pith_short_16","alias_value":"D7VLL33GC2OJ7PF4","created_at":"2026-07-05T00:45:56Z"},{"alias_kind":"pith_short_8","alias_value":"D7VLL33G","created_at":"2026-07-05T00:45:56Z"}],"graph_snapshots":[{"event_id":"sha256:2bdea7982487235ff6a1f1cd74a5e8ba862514f3216e58f106277317c3b2003a","target":"graph","created_at":"2026-07-05T00:45:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2003.02436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce \"talking-heads attention\" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.","authors_text":"Le Hou, Nan Ding, Noam Shazeer, Youlong Cheng, Zhenzhong Lan","cross_cats":["cs.NE","cs.SD","eess.AS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-05T05:17:17Z","title":"Talking-Heads Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02436","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:c2ec5634d2a6c0249ded2938687ec95845a76d246108f9e74747e2e08a7610f6","target":"record","created_at":"2026-07-05T00:45:56Z","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":"80d1c337000830737848a4391c6f4defa1a2387f68cbde76fd72cf3ad2a69d71","cross_cats_sorted":["cs.NE","cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-05T05:17:17Z","title_canon_sha256":"75b956b0d3615c1a96bf265ba58d92b153d30a07fb95f2907f6db0fb3b41442b"},"schema_version":"1.0","source":{"id":"2003.02436","kind":"arxiv","version":1}},"canonical_sha256":"1feab5ef66169c9fbcbcb90c691151ddf57eca52217880c1041ef6ea3da16eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1feab5ef66169c9fbcbcb90c691151ddf57eca52217880c1041ef6ea3da16eb6","first_computed_at":"2026-07-05T00:45:56.498692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:45:56.498692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FtPqzy5QH0pHKZ0zF0zSu/RRApv21IY6gpLGyxVlmG56YBQSPu70IVUwu2pkC3a0GUuxVEUfITtGRGYGfaDICA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:45:56.499168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.02436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ec5634d2a6c0249ded2938687ec95845a76d246108f9e74747e2e08a7610f6","sha256:2bdea7982487235ff6a1f1cd74a5e8ba862514f3216e58f106277317c3b2003a"],"state_sha256":"91be9f15956f36fef318bfb3338b4c4a2f5fc5a10dbd01cd21598d400f290cbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpXuMHJaOf+u8OjO3ZrtSXhTZQ1lY3Wr5r3E9MunjD2HW2zfpSfZdHb1ow4dpXaGckCdebaIMKFSYTBXW/3yAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T04:07:57.486526Z","bundle_sha256":"e3352c8746f79473287259cb74743836f806860358d3eb2da0f5a4dc0692a811"}}