{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2PD2Q6VTZOI4TKAPZDU7FEK4UH","short_pith_number":"pith:2PD2Q6VT","canonical_record":{"source":{"id":"2110.02782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T14:01:56Z","cross_cats_sorted":[],"title_canon_sha256":"e41ce9e521d1f328d7cc187bc6020bba66e8f3f8c17e8a4e373316cf6cf8c517","abstract_canon_sha256":"8e832b35d2a0d582f618e7a687536f692bc7ba609b6869c669bc57202f9415ee"},"schema_version":"1.0"},"canonical_sha256":"d3c7a87ab3cb91c9a80fc8e9f2915ca1d82ead9fc11a1f1713909bedf50a342b","source":{"kind":"arxiv","id":"2110.02782","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02782","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02782v2","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02782","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_12","alias_value":"2PD2Q6VTZOI4","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_16","alias_value":"2PD2Q6VTZOI4TKAP","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_8","alias_value":"2PD2Q6VT","created_at":"2026-07-05T03:36:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2PD2Q6VTZOI4TKAPZDU7FEK4UH","target":"record","payload":{"canonical_record":{"source":{"id":"2110.02782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T14:01:56Z","cross_cats_sorted":[],"title_canon_sha256":"e41ce9e521d1f328d7cc187bc6020bba66e8f3f8c17e8a4e373316cf6cf8c517","abstract_canon_sha256":"8e832b35d2a0d582f618e7a687536f692bc7ba609b6869c669bc57202f9415ee"},"schema_version":"1.0"},"canonical_sha256":"d3c7a87ab3cb91c9a80fc8e9f2915ca1d82ead9fc11a1f1713909bedf50a342b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:57.449549Z","signature_b64":"hIeMhIF3AuA6b0gxzIgFHoXHCUx/1TjygkN4yePx5UTSddam/p57oZSjqldexjp1BUGc4gjTa5aT0POgYQMQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3c7a87ab3cb91c9a80fc8e9f2915ca1d82ead9fc11a1f1713909bedf50a342b","last_reissued_at":"2026-07-05T03:36:57.448889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:57.448889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.02782","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":"2026-07-05T03:36:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EPP+aX0Vmax8+sLMDRORnHOZEZcz2S6ysUyReviCWvZQgdOT2uotTqNaa8TlcMnrCvrCODGk9v7q/TLWp4frAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:10:54.207544Z"},"content_sha256":"3c1afe0ac9a4f8137e56e4d0df51752ff1ee7568641e296b582efccf6a8c8695","schema_version":"1.0","event_id":"sha256:3c1afe0ac9a4f8137e56e4d0df51752ff1ee7568641e296b582efccf6a8c8695"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2PD2Q6VTZOI4TKAPZDU7FEK4UH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How BPE Affects Memorization in Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dieuwke Hupkes, Eugene Kharitonov, Marco Baroni","submitted_at":"2021-10-06T14:01:56Z","abstract_excerpt":"Training data memorization in NLP can both be beneficial (e.g., closed-book QA) and undesirable (personal data extraction). In any case, successful model training requires a non-trivial amount of memorization to store word spellings, various linguistic idiosyncrasies and common knowledge. However, little is known about what affects the memorization behavior of NLP models, as the field tends to focus on the equally important question of generalization. In this work, we demonstrate that the size of the subword vocabulary learned by Byte-Pair Encoding (BPE) greatly affects both ability and tenden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02782","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/2110.02782/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":"2026-07-05T03:36:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHIBqHNgCL/wX25OlBqRSkBRIk9hRakMD6/CjCT9z9EmCcGlm8wIR3pfhorXottiTmy4UTYFtZ6krF309Fl3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:10:54.208054Z"},"content_sha256":"1e434de7672a750324d4b73fff4e6126e7b820bcf7f9dd705d943c77888a0c51","schema_version":"1.0","event_id":"sha256:1e434de7672a750324d4b73fff4e6126e7b820bcf7f9dd705d943c77888a0c51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH/bundle.json","state_url":"https://pith.science/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH/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":"2026-08-05T23:10:54Z","links":{"resolver":"https://pith.science/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH","bundle":"https://pith.science/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH/bundle.json","state":"https://pith.science/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PD2Q6VTZOI4TKAPZDU7FEK4UH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2PD2Q6VTZOI4TKAPZDU7FEK4UH","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":"8e832b35d2a0d582f618e7a687536f692bc7ba609b6869c669bc57202f9415ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T14:01:56Z","title_canon_sha256":"e41ce9e521d1f328d7cc187bc6020bba66e8f3f8c17e8a4e373316cf6cf8c517"},"schema_version":"1.0","source":{"id":"2110.02782","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02782","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02782v2","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02782","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_12","alias_value":"2PD2Q6VTZOI4","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_16","alias_value":"2PD2Q6VTZOI4TKAP","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_8","alias_value":"2PD2Q6VT","created_at":"2026-07-05T03:36:57Z"}],"graph_snapshots":[{"event_id":"sha256:1e434de7672a750324d4b73fff4e6126e7b820bcf7f9dd705d943c77888a0c51","target":"graph","created_at":"2026-07-05T03:36:57Z","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/2110.02782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training data memorization in NLP can both be beneficial (e.g., closed-book QA) and undesirable (personal data extraction). In any case, successful model training requires a non-trivial amount of memorization to store word spellings, various linguistic idiosyncrasies and common knowledge. However, little is known about what affects the memorization behavior of NLP models, as the field tends to focus on the equally important question of generalization. In this work, we demonstrate that the size of the subword vocabulary learned by Byte-Pair Encoding (BPE) greatly affects both ability and tenden","authors_text":"Dieuwke Hupkes, Eugene Kharitonov, Marco Baroni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T14:01:56Z","title":"How BPE Affects Memorization in Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02782","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":"sha256:3c1afe0ac9a4f8137e56e4d0df51752ff1ee7568641e296b582efccf6a8c8695","target":"record","created_at":"2026-07-05T03:36:57Z","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":"8e832b35d2a0d582f618e7a687536f692bc7ba609b6869c669bc57202f9415ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T14:01:56Z","title_canon_sha256":"e41ce9e521d1f328d7cc187bc6020bba66e8f3f8c17e8a4e373316cf6cf8c517"},"schema_version":"1.0","source":{"id":"2110.02782","kind":"arxiv","version":2}},"canonical_sha256":"d3c7a87ab3cb91c9a80fc8e9f2915ca1d82ead9fc11a1f1713909bedf50a342b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3c7a87ab3cb91c9a80fc8e9f2915ca1d82ead9fc11a1f1713909bedf50a342b","first_computed_at":"2026-07-05T03:36:57.448889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:57.448889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hIeMhIF3AuA6b0gxzIgFHoXHCUx/1TjygkN4yePx5UTSddam/p57oZSjqldexjp1BUGc4gjTa5aT0POgYQMQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:57.449549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02782","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c1afe0ac9a4f8137e56e4d0df51752ff1ee7568641e296b582efccf6a8c8695","sha256:1e434de7672a750324d4b73fff4e6126e7b820bcf7f9dd705d943c77888a0c51"],"state_sha256":"51bc92915589f5aeab1ce42054a7d5a3c4b8f56670316fe5e5b2bdf9fdc4d0ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHkjU23EKsVwItudjwUqNI8RxJLA7vGG8kVHgt5XNye57sv/5V9E+gcSCV7lvM5wq853pBph9DZTJdYOUOqbDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:10:54.211903Z","bundle_sha256":"36b1e9fa68247f55b6a37d3ff86f449ede83bab76cc40462f6191f949165e36a"}}