{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KVHGOYXX5RWYEZFU5CUQ3YDAI7","short_pith_number":"pith:KVHGOYXX","canonical_record":{"source":{"id":"2410.05258","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T17:57:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"247f6e1950041bdd09166ab4ec3316568bcf6ec083767d7b10fbfcfd959e0152","abstract_canon_sha256":"946c55f645da7bb397614540d7f593df315278cca3555aa38d6f5dd168f37acc"},"schema_version":"1.0"},"canonical_sha256":"554e6762f7ec6d8264b4e8a90de06047f397c0e5165df852b6d6b29c8c05f004","source":{"kind":"arxiv","id":"2410.05258","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05258","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05258v2","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05258","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"KVHGOYXX5RWY","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"KVHGOYXX5RWYEZFU","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"KVHGOYXX","created_at":"2026-07-05T10:45:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KVHGOYXX5RWYEZFU5CUQ3YDAI7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.05258","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T17:57:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"247f6e1950041bdd09166ab4ec3316568bcf6ec083767d7b10fbfcfd959e0152","abstract_canon_sha256":"946c55f645da7bb397614540d7f593df315278cca3555aa38d6f5dd168f37acc"},"schema_version":"1.0"},"canonical_sha256":"554e6762f7ec6d8264b4e8a90de06047f397c0e5165df852b6d6b29c8c05f004","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:12.382806Z","signature_b64":"h/nh+xRxq5PneZXEKGnE6e+q4v1uAo7F0PAVkM7m7/tdEdjCDS06tsAFmUQK6PBcWMmkppD52iAE1Nx+ehpNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"554e6762f7ec6d8264b4e8a90de06047f397c0e5165df852b6d6b29c8c05f004","last_reissued_at":"2026-07-05T10:45:12.382240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:12.382240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.05258","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":"2026-07-05T10:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJqQiZgPvfRiQZPewhMBQwU7tftfRIzydTthC2KGgDHaRurPf92m2y8do2d4rvUkjP5t0ZyWz035bjwGXVlRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:37:46.884924Z"},"content_sha256":"2a724365c99b4c0cdec57e345980c38a73db04fb701ad03eea57ae4803706913","schema_version":"1.0","event_id":"sha256:2a724365c99b4c0cdec57e345980c38a73db04fb701ad03eea57ae4803706913"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KVHGOYXX5RWYEZFU5CUQ3YDAI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differential Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Gao Huang, Li Dong, Tianzhu Ye, Yi Zhu, Yuqing Xia, Yutao Sun","submitted_at":"2024-10-07T17:57:38Z","abstract_excerpt":"Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism calculates attention scores as the difference between two separate softmax attention maps. The subtraction cancels noise, promoting the emergence of sparse attention patterns. Experimental results on language modeling show that Diff Transformer outperforms Transformer in various settings of scaling up model size and training tokens. More intriguingly, it offers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05258","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/2410.05258/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":"2026-07-05T10:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wyrVpsE/R1Fb6cWB4xSUtXwF0vtK2e9LW9uFXr4NPKaafPRY5c8CDSF0kkMGw+ljG94Vi8AxSEdyyUDh7F2WBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:37:46.885312Z"},"content_sha256":"53020683fb1805a749b5700cbbf906bad30ebe03e837e6b050ed208e0230caf3","schema_version":"1.0","event_id":"sha256:53020683fb1805a749b5700cbbf906bad30ebe03e837e6b050ed208e0230caf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7/bundle.json","state_url":"https://pith.science/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7/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":"2026-08-20T09:37:46Z","links":{"resolver":"https://pith.science/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7","bundle":"https://pith.science/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7/bundle.json","state":"https://pith.science/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KVHGOYXX5RWYEZFU5CUQ3YDAI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KVHGOYXX5RWYEZFU5CUQ3YDAI7","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":"946c55f645da7bb397614540d7f593df315278cca3555aa38d6f5dd168f37acc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T17:57:38Z","title_canon_sha256":"247f6e1950041bdd09166ab4ec3316568bcf6ec083767d7b10fbfcfd959e0152"},"schema_version":"1.0","source":{"id":"2410.05258","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05258","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05258v2","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05258","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"KVHGOYXX5RWY","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"KVHGOYXX5RWYEZFU","created_at":"2026-07-05T10:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"KVHGOYXX","created_at":"2026-07-05T10:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:53020683fb1805a749b5700cbbf906bad30ebe03e837e6b050ed208e0230caf3","target":"graph","created_at":"2026-07-05T10:45:12Z","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/2410.05258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism calculates attention scores as the difference between two separate softmax attention maps. The subtraction cancels noise, promoting the emergence of sparse attention patterns. Experimental results on language modeling show that Diff Transformer outperforms Transformer in various settings of scaling up model size and training tokens. More intriguingly, it offers ","authors_text":"Furu Wei, Gao Huang, Li Dong, Tianzhu Ye, Yi Zhu, Yuqing Xia, Yutao Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T17:57:38Z","title":"Differential Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05258","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":"sha256:2a724365c99b4c0cdec57e345980c38a73db04fb701ad03eea57ae4803706913","target":"record","created_at":"2026-07-05T10:45:12Z","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":"946c55f645da7bb397614540d7f593df315278cca3555aa38d6f5dd168f37acc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T17:57:38Z","title_canon_sha256":"247f6e1950041bdd09166ab4ec3316568bcf6ec083767d7b10fbfcfd959e0152"},"schema_version":"1.0","source":{"id":"2410.05258","kind":"arxiv","version":2}},"canonical_sha256":"554e6762f7ec6d8264b4e8a90de06047f397c0e5165df852b6d6b29c8c05f004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"554e6762f7ec6d8264b4e8a90de06047f397c0e5165df852b6d6b29c8c05f004","first_computed_at":"2026-07-05T10:45:12.382240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:12.382240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h/nh+xRxq5PneZXEKGnE6e+q4v1uAo7F0PAVkM7m7/tdEdjCDS06tsAFmUQK6PBcWMmkppD52iAE1Nx+ehpNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:12.382806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05258","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a724365c99b4c0cdec57e345980c38a73db04fb701ad03eea57ae4803706913","sha256:53020683fb1805a749b5700cbbf906bad30ebe03e837e6b050ed208e0230caf3"],"state_sha256":"075eb511fbfe952ce78d36cc38d13691bf98498413bd71d1bb3f94345071b868"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SI1whFAS4uWT6c0ovKxzAmzCJp5k/Qz4HAVMPzjW4bEw/GumMOeqJ+MJKJR1DxuGsCTRk5VQyzRfZ7KbYfZfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T09:37:46.887849Z","bundle_sha256":"7f37d97053a56a46418b0a0a20c882f4898fe4e5f374acd04d12abf72b41f1a5"}}