{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DUFY6EIVHL52P72H7WRCH3BZVI","short_pith_number":"pith:DUFY6EIV","canonical_record":{"source":{"id":"2011.04393","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T12:49:39Z","cross_cats_sorted":[],"title_canon_sha256":"18ebba1ffd6ab556d446396d4e2517b5d49c2edf54cd3224fc0b2544f47662f9","abstract_canon_sha256":"f99f0a84397a1ccea449443e9d20ba93161393cf0ab86b7025453bf8c36b56fd"},"schema_version":"1.0"},"canonical_sha256":"1d0b8f11153afba7ff47fda223ec39aa2886c22e905b830fea85087737a36881","source":{"kind":"arxiv","id":"2011.04393","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04393","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04393v3","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04393","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"DUFY6EIVHL52","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"DUFY6EIVHL52P72H","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"DUFY6EIV","created_at":"2026-07-05T02:42:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DUFY6EIVHL52P72H7WRCH3BZVI","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04393","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T12:49:39Z","cross_cats_sorted":[],"title_canon_sha256":"18ebba1ffd6ab556d446396d4e2517b5d49c2edf54cd3224fc0b2544f47662f9","abstract_canon_sha256":"f99f0a84397a1ccea449443e9d20ba93161393cf0ab86b7025453bf8c36b56fd"},"schema_version":"1.0"},"canonical_sha256":"1d0b8f11153afba7ff47fda223ec39aa2886c22e905b830fea85087737a36881","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:44.776141Z","signature_b64":"hrmTXbXibCYooPmN0jmbcfZAdleZwUv4ysxFoNS2XLuM6D1t1uEKNeXt/7u/dM+d+pdbYWbBSZjr6IGB5S3dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d0b8f11153afba7ff47fda223ec39aa2886c22e905b830fea85087737a36881","last_reissued_at":"2026-07-05T02:42:44.775708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:44.775708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04393","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Di1pZy69cd0oDS7CRpddcBkQkkwBR5XCHIia55lbetF8kukUBObK5rOF2Itl7cNvq+tqMEA0PxCkbHgsuptaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:26:38.420020Z"},"content_sha256":"8a095861357a8f47341892bd2568030c7de976ceef5a1f92ff132b1eb8d742ed","schema_version":"1.0","event_id":"sha256:8a095861357a8f47341892bd2568030c7de976ceef5a1f92ff132b1eb8d742ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DUFY6EIVHL52P72H7WRCH3BZVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Positional Artefacts Propagate Through Masked Language Model Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Artur Kulmizev, Xiaoxi Mao, Ziyang Luo","submitted_at":"2020-11-09T12:49:39Z","abstract_excerpt":"In this work, we demonstrate that the contextualized word vectors derived from pretrained masked language model-based encoders share a common, perhaps undesirable pattern across layers. Namely, we find cases of persistent outlier neurons within BERT and RoBERTa's hidden state vectors that consistently bear the smallest or largest values in said vectors. In an attempt to investigate the source of this information, we introduce a neuron-level analysis method, which reveals that the outliers are closely related to information captured by positional embeddings. We also pre-train the RoBERTa-base m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04393","kind":"arxiv","version":3},"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/2011.04393/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":"2026-07-05T02:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnzfFkbpvR9/8AtK7jUituqJlU0dBVYs2DS4imIr85CkZ5bAv8kcfuYItC3ScKOHQWRZoPjgkMCgcRnmMrj5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:26:38.420699Z"},"content_sha256":"efec3c77a0c1e2ccd196f678585585ea61690c732cbf72ed04a780aa001d27ff","schema_version":"1.0","event_id":"sha256:efec3c77a0c1e2ccd196f678585585ea61690c732cbf72ed04a780aa001d27ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUFY6EIVHL52P72H7WRCH3BZVI/bundle.json","state_url":"https://pith.science/pith/DUFY6EIVHL52P72H7WRCH3BZVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUFY6EIVHL52P72H7WRCH3BZVI/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":"2026-08-24T00:26:38Z","links":{"resolver":"https://pith.science/pith/DUFY6EIVHL52P72H7WRCH3BZVI","bundle":"https://pith.science/pith/DUFY6EIVHL52P72H7WRCH3BZVI/bundle.json","state":"https://pith.science/pith/DUFY6EIVHL52P72H7WRCH3BZVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUFY6EIVHL52P72H7WRCH3BZVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DUFY6EIVHL52P72H7WRCH3BZVI","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":"f99f0a84397a1ccea449443e9d20ba93161393cf0ab86b7025453bf8c36b56fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T12:49:39Z","title_canon_sha256":"18ebba1ffd6ab556d446396d4e2517b5d49c2edf54cd3224fc0b2544f47662f9"},"schema_version":"1.0","source":{"id":"2011.04393","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04393","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04393v3","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04393","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"DUFY6EIVHL52","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"DUFY6EIVHL52P72H","created_at":"2026-07-05T02:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"DUFY6EIV","created_at":"2026-07-05T02:42:44Z"}],"graph_snapshots":[{"event_id":"sha256:efec3c77a0c1e2ccd196f678585585ea61690c732cbf72ed04a780aa001d27ff","target":"graph","created_at":"2026-07-05T02:42:44Z","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/2011.04393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we demonstrate that the contextualized word vectors derived from pretrained masked language model-based encoders share a common, perhaps undesirable pattern across layers. Namely, we find cases of persistent outlier neurons within BERT and RoBERTa's hidden state vectors that consistently bear the smallest or largest values in said vectors. In an attempt to investigate the source of this information, we introduce a neuron-level analysis method, which reveals that the outliers are closely related to information captured by positional embeddings. We also pre-train the RoBERTa-base m","authors_text":"Artur Kulmizev, Xiaoxi Mao, Ziyang Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T12:49:39Z","title":"Positional Artefacts Propagate Through Masked Language Model Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04393","kind":"arxiv","version":3},"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":"sha256:8a095861357a8f47341892bd2568030c7de976ceef5a1f92ff132b1eb8d742ed","target":"record","created_at":"2026-07-05T02:42:44Z","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":"f99f0a84397a1ccea449443e9d20ba93161393cf0ab86b7025453bf8c36b56fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-09T12:49:39Z","title_canon_sha256":"18ebba1ffd6ab556d446396d4e2517b5d49c2edf54cd3224fc0b2544f47662f9"},"schema_version":"1.0","source":{"id":"2011.04393","kind":"arxiv","version":3}},"canonical_sha256":"1d0b8f11153afba7ff47fda223ec39aa2886c22e905b830fea85087737a36881","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d0b8f11153afba7ff47fda223ec39aa2886c22e905b830fea85087737a36881","first_computed_at":"2026-07-05T02:42:44.775708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:44.775708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hrmTXbXibCYooPmN0jmbcfZAdleZwUv4ysxFoNS2XLuM6D1t1uEKNeXt/7u/dM+d+pdbYWbBSZjr6IGB5S3dAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:44.776141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04393","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a095861357a8f47341892bd2568030c7de976ceef5a1f92ff132b1eb8d742ed","sha256:efec3c77a0c1e2ccd196f678585585ea61690c732cbf72ed04a780aa001d27ff"],"state_sha256":"49e4eeb73cb968d80ca35f4ba1aa3b883c471efdc8834cdb354167015ff50b38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LEE+EIchac11dDzAh7D1Dy5EqjFj/QJxrLi2oJy0fkr7pIra9MlldnBSYhxHhn6XN92lUPPcKow19Vp9nwjcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:26:38.426888Z","bundle_sha256":"78952475483c6ae481fc3cf5debeae2bbed35ef89f7ab87e4e785b70421b3e7f"}}