{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RN7U4VOPGSUBRHCM3XDWF2GCR5","short_pith_number":"pith:RN7U4VOP","canonical_record":{"source":{"id":"2010.11859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T16:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"4eb0941cb7e838902545979a08cd872c313f6a8bb0a0726fb6a3c17874539ce8","abstract_canon_sha256":"4441eb757f314b39f0005d78460c91457122bb51de077bfb8cd6d40c7fa0293b"},"schema_version":"1.0"},"canonical_sha256":"8b7f4e55cf34a8189c4cddc762e8c28f7a587360cad51cbc4a40adc9cb44c11b","source":{"kind":"arxiv","id":"2010.11859","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11859","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11859v2","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11859","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"pith_short_12","alias_value":"RN7U4VOPGSUB","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"pith_short_16","alias_value":"RN7U4VOPGSUBRHCM","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"pith_short_8","alias_value":"RN7U4VOP","created_at":"2026-07-05T03:16:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RN7U4VOPGSUBRHCM3XDWF2GCR5","target":"record","payload":{"canonical_record":{"source":{"id":"2010.11859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T16:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"4eb0941cb7e838902545979a08cd872c313f6a8bb0a0726fb6a3c17874539ce8","abstract_canon_sha256":"4441eb757f314b39f0005d78460c91457122bb51de077bfb8cd6d40c7fa0293b"},"schema_version":"1.0"},"canonical_sha256":"8b7f4e55cf34a8189c4cddc762e8c28f7a587360cad51cbc4a40adc9cb44c11b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:06.174106Z","signature_b64":"Epik/2MpDa6yhskbN7DB5Xh2zyTgslcAVE5DQpmcRJio0SjTtkxWT9bQ4j9bPGDpg7I9m/fYoPqy6fELAd69DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b7f4e55cf34a8189c4cddc762e8c28f7a587360cad51cbc4a40adc9cb44c11b","last_reissued_at":"2026-07-05T03:16:06.173590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:06.173590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.11859","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":"2026-07-05T03:16:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KMhWssjkjhbvq8ffdlt08mmpISKngGVAgk1rKCQkN0t8ot697jsAFPPoBZcZWVrVaSfhybPCIFXfAvP7Rc9UAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:26:14.620187Z"},"content_sha256":"28f8c051387f8c402d19f76382acad1adc708200296bcd4e52c3fcec4da89ea2","schema_version":"1.0","event_id":"sha256:28f8c051387f8c402d19f76382acad1adc708200296bcd4e52c3fcec4da89ea2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RN7U4VOPGSUBRHCM3XDWF2GCR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not all parameters are born equal: Attention is mostly what you need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nikolay Bogoychev","submitted_at":"2020-10-22T16:49:18Z","abstract_excerpt":"Transformers are widely used in state-of-the-art machine translation, but the key to their success is still unknown. To gain insight into this, we consider three groups of parameters: embeddings, attention, and feed forward neural network (FFN) layers. We examine the relative importance of each by performing an ablation study where we initialise them at random and freeze them, so that their weights do not change over the course of the training. Through this, we show that the attention and FFN are equally important and fulfil the same functionality in a model. We show that the decision about wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11859","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/2010.11859/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":"2026-07-05T03:16:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWFZg0Y9I1vYOCq5ofx5zunLTEqHn7cYtDKocyXUyjyUVZ6dgrYyZm3g48srGNqtBNEO36NY2ZsXDTuqpl5HBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:26:14.620668Z"},"content_sha256":"5421249d00d632c298d8982f9bb1f2f63a68855fd8df745b82718b0c579d6ae6","schema_version":"1.0","event_id":"sha256:5421249d00d632c298d8982f9bb1f2f63a68855fd8df745b82718b0c579d6ae6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5/bundle.json","state_url":"https://pith.science/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5/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":"2026-08-15T11:26:14Z","links":{"resolver":"https://pith.science/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5","bundle":"https://pith.science/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5/bundle.json","state":"https://pith.science/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RN7U4VOPGSUBRHCM3XDWF2GCR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RN7U4VOPGSUBRHCM3XDWF2GCR5","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":"4441eb757f314b39f0005d78460c91457122bb51de077bfb8cd6d40c7fa0293b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T16:49:18Z","title_canon_sha256":"4eb0941cb7e838902545979a08cd872c313f6a8bb0a0726fb6a3c17874539ce8"},"schema_version":"1.0","source":{"id":"2010.11859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11859","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11859v2","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11859","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"pith_short_12","alias_value":"RN7U4VOPGSUB","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"pith_short_16","alias_value":"RN7U4VOPGSUBRHCM","created_at":"2026-07-05T03:16:06Z"},{"alias_kind":"pith_short_8","alias_value":"RN7U4VOP","created_at":"2026-07-05T03:16:06Z"}],"graph_snapshots":[{"event_id":"sha256:5421249d00d632c298d8982f9bb1f2f63a68855fd8df745b82718b0c579d6ae6","target":"graph","created_at":"2026-07-05T03:16:06Z","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/2010.11859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers are widely used in state-of-the-art machine translation, but the key to their success is still unknown. To gain insight into this, we consider three groups of parameters: embeddings, attention, and feed forward neural network (FFN) layers. We examine the relative importance of each by performing an ablation study where we initialise them at random and freeze them, so that their weights do not change over the course of the training. Through this, we show that the attention and FFN are equally important and fulfil the same functionality in a model. We show that the decision about wh","authors_text":"Nikolay Bogoychev","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T16:49:18Z","title":"Not all parameters are born equal: Attention is mostly what you need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11859","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":"sha256:28f8c051387f8c402d19f76382acad1adc708200296bcd4e52c3fcec4da89ea2","target":"record","created_at":"2026-07-05T03:16:06Z","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":"4441eb757f314b39f0005d78460c91457122bb51de077bfb8cd6d40c7fa0293b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T16:49:18Z","title_canon_sha256":"4eb0941cb7e838902545979a08cd872c313f6a8bb0a0726fb6a3c17874539ce8"},"schema_version":"1.0","source":{"id":"2010.11859","kind":"arxiv","version":2}},"canonical_sha256":"8b7f4e55cf34a8189c4cddc762e8c28f7a587360cad51cbc4a40adc9cb44c11b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b7f4e55cf34a8189c4cddc762e8c28f7a587360cad51cbc4a40adc9cb44c11b","first_computed_at":"2026-07-05T03:16:06.173590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:16:06.173590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Epik/2MpDa6yhskbN7DB5Xh2zyTgslcAVE5DQpmcRJio0SjTtkxWT9bQ4j9bPGDpg7I9m/fYoPqy6fELAd69DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:16:06.174106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28f8c051387f8c402d19f76382acad1adc708200296bcd4e52c3fcec4da89ea2","sha256:5421249d00d632c298d8982f9bb1f2f63a68855fd8df745b82718b0c579d6ae6"],"state_sha256":"f6f710e366688d16e626ea8365f2e828a1b1fff933bb4036b9605f5a723e9f78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72j3YDepnMAp+vnHixLqYzenNcjlghSQb+Q2wOtePvPZjen8s4Ye3Kvgvyk1IpQfUA0uxcz7wNaQafHt2hePDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:26:14.624188Z","bundle_sha256":"acbccb31e5f36766b61df93d17e3753e8e3b9304a1857a16b5fd25a976fdd591"}}