{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FTN3NEOMYNL2BWVRKLITK4ZZBN","short_pith_number":"pith:FTN3NEOM","canonical_record":{"source":{"id":"2104.07012","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T17:52:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cbb3cd2894e8c360c3d48eb1922b65aedf8f4663aae898a5f1304791bea66fa","abstract_canon_sha256":"28a6aa98abb456d522ad3b86ace6647a50a6e10d3189d4deaf123b67ea724381"},"schema_version":"1.0"},"canonical_sha256":"2cdbb691ccc357a0dab152d13573390b7b1011190a79132b3a34d73aa31e707b","source":{"kind":"arxiv","id":"2104.07012","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07012","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07012v2","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07012","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"FTN3NEOMYNL2","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"FTN3NEOMYNL2BWVR","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"FTN3NEOM","created_at":"2026-07-05T03:20:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FTN3NEOMYNL2BWVRKLITK4ZZBN","target":"record","payload":{"canonical_record":{"source":{"id":"2104.07012","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T17:52:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cbb3cd2894e8c360c3d48eb1922b65aedf8f4663aae898a5f1304791bea66fa","abstract_canon_sha256":"28a6aa98abb456d522ad3b86ace6647a50a6e10d3189d4deaf123b67ea724381"},"schema_version":"1.0"},"canonical_sha256":"2cdbb691ccc357a0dab152d13573390b7b1011190a79132b3a34d73aa31e707b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:20.559163Z","signature_b64":"yxLgIfD3kqgsnTQBoke5ZJDsJirny8j4PAxlABwJhkPRGIK+ZWPxDm7dXaIw0TltME4agToucrcg3hkE/ercAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cdbb691ccc357a0dab152d13573390b7b1011190a79132b3a34d73aa31e707b","last_reissued_at":"2026-07-05T03:20:20.558767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:20.558767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.07012","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":"2026-07-05T03:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g+yf2rIrmI7Mc5J1+K0LrWUWIyA+dPECnhW9sjFuVCaJU3j4tpRgjEFabKNnJfgBDP9PIHUuFqpqA7pbcFTwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:54:38.281935Z"},"content_sha256":"f33cb70b8816aacd3ed4fe71a1ecddd4880c76cd132bda5c352cc5ec6871acb5","schema_version":"1.0","event_id":"sha256:f33cb70b8816aacd3ed4fe71a1ecddd4880c76cd132bda5c352cc5ec6871acb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FTN3NEOMYNL2BWVRKLITK4ZZBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Attention with Linear Units","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Ivan Titov, Rico Sennrich","submitted_at":"2021-04-14T17:52:38Z","abstract_excerpt":"Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07012","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/2104.07012/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":"2026-07-05T03:20:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Btyv9U4SKvQJ9/uvxCXQITWHptyJJvFlWWTAbv85bjEFLGgNtLPgh4xZcCaUrpTsDnjy+0N9+mqNYTd1sn0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:54:38.282853Z"},"content_sha256":"9c3b37799261ac22aa15276d7a9744dc0b82dfbc3292c63ccfd3dddc38f04cc6","schema_version":"1.0","event_id":"sha256:9c3b37799261ac22aa15276d7a9744dc0b82dfbc3292c63ccfd3dddc38f04cc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN/bundle.json","state_url":"https://pith.science/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN/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":"2026-08-09T05:54:38Z","links":{"resolver":"https://pith.science/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN","bundle":"https://pith.science/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN/bundle.json","state":"https://pith.science/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FTN3NEOMYNL2BWVRKLITK4ZZBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FTN3NEOMYNL2BWVRKLITK4ZZBN","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":"28a6aa98abb456d522ad3b86ace6647a50a6e10d3189d4deaf123b67ea724381","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T17:52:38Z","title_canon_sha256":"5cbb3cd2894e8c360c3d48eb1922b65aedf8f4663aae898a5f1304791bea66fa"},"schema_version":"1.0","source":{"id":"2104.07012","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07012","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07012v2","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07012","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"FTN3NEOMYNL2","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"FTN3NEOMYNL2BWVR","created_at":"2026-07-05T03:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"FTN3NEOM","created_at":"2026-07-05T03:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:9c3b37799261ac22aa15276d7a9744dc0b82dfbc3292c63ccfd3dddc38f04cc6","target":"graph","created_at":"2026-07-05T03:20:20Z","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/2104.07012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than","authors_text":"Biao Zhang, Ivan Titov, Rico Sennrich","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T17:52:38Z","title":"Sparse Attention with Linear Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07012","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:f33cb70b8816aacd3ed4fe71a1ecddd4880c76cd132bda5c352cc5ec6871acb5","target":"record","created_at":"2026-07-05T03:20:20Z","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":"28a6aa98abb456d522ad3b86ace6647a50a6e10d3189d4deaf123b67ea724381","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T17:52:38Z","title_canon_sha256":"5cbb3cd2894e8c360c3d48eb1922b65aedf8f4663aae898a5f1304791bea66fa"},"schema_version":"1.0","source":{"id":"2104.07012","kind":"arxiv","version":2}},"canonical_sha256":"2cdbb691ccc357a0dab152d13573390b7b1011190a79132b3a34d73aa31e707b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cdbb691ccc357a0dab152d13573390b7b1011190a79132b3a34d73aa31e707b","first_computed_at":"2026-07-05T03:20:20.558767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:20.558767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yxLgIfD3kqgsnTQBoke5ZJDsJirny8j4PAxlABwJhkPRGIK+ZWPxDm7dXaIw0TltME4agToucrcg3hkE/ercAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:20.559163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07012","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f33cb70b8816aacd3ed4fe71a1ecddd4880c76cd132bda5c352cc5ec6871acb5","sha256:9c3b37799261ac22aa15276d7a9744dc0b82dfbc3292c63ccfd3dddc38f04cc6"],"state_sha256":"4a5adfc0f76e3bf821b37180122d7fc7ca5df3c7e4cf6b5236fde824803d4b57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2s2t07QhSQDlHlHnSCbViqQodk3isLhxoBjUMyicon2Wx5TNOBwcxCzhUoMspRY1yOlkP5aIQIrvu95K4wF+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:54:38.289636Z","bundle_sha256":"ab539a2678886cbc626b1e1d34534c7f49b3daec8ca24e41f2c0d2cbd7bded1a"}}