{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CXPXXMQRMHRHYZ2C7KEJ4A4ORY","short_pith_number":"pith:CXPXXMQR","canonical_record":{"source":{"id":"1706.03762","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:57:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a1c934d3d98f3cefede93ebb74d0c4c2bac7ac9cc4f467d253ef8f87a2d6aad","abstract_canon_sha256":"1da1dd70762acfc21bc9dee470bab7c071938fcb9e78ac84e3f65cb26a5094be"},"schema_version":"1.0"},"canonical_sha256":"15df7bb21161e27c6742fa889e038e8e3fa1b31e357d8d314219b0007b4f52bc","source":{"kind":"arxiv","id":"1706.03762","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03762","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03762v7","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03762","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"CXPXXMQRMHRH","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"CXPXXMQRMHRHYZ2C","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"CXPXXMQR","created_at":"2026-07-05T06:36:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CXPXXMQRMHRHYZ2C7KEJ4A4ORY","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03762","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:57:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a1c934d3d98f3cefede93ebb74d0c4c2bac7ac9cc4f467d253ef8f87a2d6aad","abstract_canon_sha256":"1da1dd70762acfc21bc9dee470bab7c071938fcb9e78ac84e3f65cb26a5094be"},"schema_version":"1.0"},"canonical_sha256":"15df7bb21161e27c6742fa889e038e8e3fa1b31e357d8d314219b0007b4f52bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:50.874935Z","signature_b64":"Lqp4L7ojBUhKv3worm0Mvo1HSXW8pJ5YOED+Dw9W5vHSEtYUg25q/L1LNA3Kv1m/OLLEUHFQ1eGCkj0US+lrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15df7bb21161e27c6742fa889e038e8e3fa1b31e357d8d314219b0007b4f52bc","last_reissued_at":"2026-07-05T06:36:50.874443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:50.874443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03762","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:36:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaLZiqxxvQUlrWqbL0An1tfZ8S59KyRmCYovoAKQnUJl66VK0OVPp5MwQ+8ccflfv4tsCyXKoGLhPnMYGOpiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-11-15T01:42:21.356440Z"},"content_sha256":"272d153ba365571ae095db2712bd7065bdf8c1d087e4c9efcce76c89f78f4f41","schema_version":"1.0","event_id":"sha256:272d153ba365571ae095db2712bd7065bdf8c1d087e4c9efcce76c89f78f4f41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CXPXXMQRMHRHYZ2C7KEJ4A4ORY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention Is All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A sequence model built entirely from self-attention, with no recurrence or convolution, sets new translation state of the art while training far faster than the systems it replaces.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aidan N. Gomez, Ashish Vaswani, Illia Polosukhin, Jakob Uszkoreit, Llion Jones, Lukasz Kaiser, Niki Parmar, Noam Shazeer","submitted_at":"2017-06-12T17:57:34Z","abstract_excerpt":"The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the W"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Central claim unavailable from malformed reader payload.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Load-bearing assumption unavailable from malformed reader payload.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pith review generated a malformed one-line summary.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A sequence model built entirely from self-attention, with no recurrence or convolution, sets new translation state of the art while training far faster than the systems it replaces.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c13dd4e1a264bc9a5fbf570dc09aacd8b137c5c5994ba63c28daa280732c39f0"},"source":{"id":"1706.03762","kind":"arxiv","version":7},"verdict":{"id":"81eb988f-822e-42f0-8984-0fe8c2984f67","model_set":{"reader":"claude-opus-4-7"},"created_at":"2026-05-08T22:11:17.225364Z","strongest_claim":"Central claim unavailable from malformed reader payload.","one_line_summary":"Pith review generated a malformed one-line summary.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Load-bearing assumption unavailable from malformed reader payload.","pith_extraction_headline":"A sequence model built entirely from self-attention, with no recurrence or convolution, sets new translation state of the art while training far faster than the systems it replaces."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1706.03762/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":40,"sample":[{"doi":"","year":2016,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","ref_index":1,"cited_arxiv_id":"1607.06450","is_internal_anchor":false},{"doi":"","year":2014,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","ref_index":2,"cited_arxiv_id":"1409.0473","is_internal_anchor":true},{"doi":"","year":2017,"title":"Massive Exploration of Neural Machine Translation Architectures","work_id":"0dfbd025-1db0-43eb-b365-7a6a4327eec3","ref_index":3,"cited_arxiv_id":"1703.03906","is_internal_anchor":false},{"doi":"","year":2016,"title":"Long Short-Term Memory-Networks for Machine Reading","work_id":"8d5f976c-3778-4f8f-98aa-4d138f8c1f34","ref_index":4,"cited_arxiv_id":"1601.06733","is_internal_anchor":false},{"doi":"","year":2014,"title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","work_id":"af085a26-bb72-4b1a-8e38-107776555081","ref_index":5,"cited_arxiv_id":"1406.1078","is_internal_anchor":true}],"resolved_work":40,"snapshot_sha256":"272994bb36d63702f9d9b8a62bcd4d92051f539a04cf59c1e50bb2d2d87534ff","internal_anchors":7},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"81eb988f-822e-42f0-8984-0fe8c2984f67"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:36:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqfmRQUAm2vemqZwUCbjemfADuk1USsG20jA1QaMv1mErtssKmpZdnBAPN9PStiAPRbNTQY5mcU2ZubfzfVICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-11-15T01:42:21.356990Z"},"content_sha256":"9626c9393a3feebc78742d4531a43d3469202ad77992b27f67af68f6cce13df6","schema_version":"1.0","event_id":"sha256:9626c9393a3feebc78742d4531a43d3469202ad77992b27f67af68f6cce13df6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY/bundle.json","state_url":"https://pith.science/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY/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":"2026-11-15T01:42:21Z","links":{"resolver":"https://pith.science/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY","bundle":"https://pith.science/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY/bundle.json","state":"https://pith.science/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXPXXMQRMHRHYZ2C7KEJ4A4ORY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CXPXXMQRMHRHYZ2C7KEJ4A4ORY","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":"1da1dd70762acfc21bc9dee470bab7c071938fcb9e78ac84e3f65cb26a5094be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:57:34Z","title_canon_sha256":"4a1c934d3d98f3cefede93ebb74d0c4c2bac7ac9cc4f467d253ef8f87a2d6aad"},"schema_version":"1.0","source":{"id":"1706.03762","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03762","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03762v7","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03762","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"CXPXXMQRMHRH","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"CXPXXMQRMHRHYZ2C","created_at":"2026-07-05T06:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"CXPXXMQR","created_at":"2026-07-05T06:36:50Z"}],"graph_snapshots":[{"event_id":"sha256:9626c9393a3feebc78742d4531a43d3469202ad77992b27f67af68f6cce13df6","target":"graph","created_at":"2026-07-05T06:36:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Central claim unavailable from malformed reader payload."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Load-bearing assumption unavailable from malformed reader payload."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Pith review generated a malformed one-line summary."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A sequence model built entirely from self-attention, with no recurrence or convolution, sets new translation state of the art while training far faster than the systems it replaces."}],"snapshot_sha256":"c13dd4e1a264bc9a5fbf570dc09aacd8b137c5c5994ba63c28daa280732c39f0"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1706.03762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the W","authors_text":"Aidan N. Gomez, Ashish Vaswani, Illia Polosukhin, Jakob Uszkoreit, Llion Jones, Lukasz Kaiser, Niki Parmar, Noam Shazeer","cross_cats":["cs.LG"],"headline":"A sequence model built entirely from self-attention, with no recurrence or convolution, sets new translation state of the art while training far faster than the systems it replaces.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:57:34Z","title":"Attention Is All You Need"},"references":{"count":40,"internal_anchors":7,"resolved_work":40,"sample":[{"cited_arxiv_id":"1607.06450","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","year":2016},{"cited_arxiv_id":"1409.0473","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","year":2014},{"cited_arxiv_id":"1703.03906","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Massive Exploration of Neural Machine Translation Architectures","work_id":"0dfbd025-1db0-43eb-b365-7a6a4327eec3","year":2017},{"cited_arxiv_id":"1601.06733","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Long Short-Term Memory-Networks for Machine Reading","work_id":"8d5f976c-3778-4f8f-98aa-4d138f8c1f34","year":2016},{"cited_arxiv_id":"1406.1078","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","work_id":"af085a26-bb72-4b1a-8e38-107776555081","year":2014}],"snapshot_sha256":"272994bb36d63702f9d9b8a62bcd4d92051f539a04cf59c1e50bb2d2d87534ff"},"source":{"id":"1706.03762","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-08T22:11:17.225364Z","id":"81eb988f-822e-42f0-8984-0fe8c2984f67","model_set":{"reader":"claude-opus-4-7"},"one_line_summary":"Pith review generated a malformed one-line summary.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A sequence model built entirely from self-attention, with no recurrence or convolution, sets new translation state of the art while training far faster than the systems it replaces.","strongest_claim":"Central claim unavailable from malformed reader payload.","weakest_assumption":"Load-bearing assumption unavailable from malformed reader payload."}},"verdict_id":"81eb988f-822e-42f0-8984-0fe8c2984f67"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:272d153ba365571ae095db2712bd7065bdf8c1d087e4c9efcce76c89f78f4f41","target":"record","created_at":"2026-07-05T06:36:50Z","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":"1da1dd70762acfc21bc9dee470bab7c071938fcb9e78ac84e3f65cb26a5094be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:57:34Z","title_canon_sha256":"4a1c934d3d98f3cefede93ebb74d0c4c2bac7ac9cc4f467d253ef8f87a2d6aad"},"schema_version":"1.0","source":{"id":"1706.03762","kind":"arxiv","version":7}},"canonical_sha256":"15df7bb21161e27c6742fa889e038e8e3fa1b31e357d8d314219b0007b4f52bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15df7bb21161e27c6742fa889e038e8e3fa1b31e357d8d314219b0007b4f52bc","first_computed_at":"2026-07-05T06:36:50.874443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:50.874443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lqp4L7ojBUhKv3worm0Mvo1HSXW8pJ5YOED+Dw9W5vHSEtYUg25q/L1LNA3Kv1m/OLLEUHFQ1eGCkj0US+lrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:50.874935Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03762","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:272d153ba365571ae095db2712bd7065bdf8c1d087e4c9efcce76c89f78f4f41","sha256:9626c9393a3feebc78742d4531a43d3469202ad77992b27f67af68f6cce13df6"],"state_sha256":"cb2209763373e31a094d5cee7611b7565bf985e8089505b69d11dfab93fae1e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfNUeRiALJNTmPJhSrYgqE95yVhnJm4Yrz9SGyUX+h4F2mrvG3Oivnt//V5OSzlc5K9pezCsg1yP1XeCs1ndBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-11-15T01:42:21.362497Z","bundle_sha256":"cfebaa5435939184c31716081c10226d8925ddc0f6e2377a83ca5c4e178d1d2f"}}