{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:L4FBXN6N55RJZNGNIHVLAEPVXM","short_pith_number":"pith:L4FBXN6N","canonical_record":{"source":{"id":"1904.06707","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T15:26:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4fa27bca99c88720fedd885bd8c3e040a67f102f976a3a3ce406da5f287799a0","abstract_canon_sha256":"2dfba22748926ab901db1fff90ae2d63a6270a82ab0b954380e61d9ed318a4ad"},"schema_version":"1.0"},"canonical_sha256":"5f0a1bb7cdef629cb4cd41eab011f5bb2c22bfdf26180f617131252a847fdc11","source":{"kind":"arxiv","id":"1904.06707","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06707","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06707v4","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06707","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"pith_short_12","alias_value":"L4FBXN6N55RJ","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"pith_short_16","alias_value":"L4FBXN6N55RJZNGN","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"pith_short_8","alias_value":"L4FBXN6N","created_at":"2026-07-05T00:23:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:L4FBXN6N55RJZNGNIHVLAEPVXM","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06707","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T15:26:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4fa27bca99c88720fedd885bd8c3e040a67f102f976a3a3ce406da5f287799a0","abstract_canon_sha256":"2dfba22748926ab901db1fff90ae2d63a6270a82ab0b954380e61d9ed318a4ad"},"schema_version":"1.0"},"canonical_sha256":"5f0a1bb7cdef629cb4cd41eab011f5bb2c22bfdf26180f617131252a847fdc11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:49.093944Z","signature_b64":"2zMbEBC4GVsQPCRM+sMyX3T9TYpzyU2unbrEhycRhZVe127CZKzReq4NFiitCWIRsjVQN/xB15bsQR8gvHM7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f0a1bb7cdef629cb4cd41eab011f5bb2c22bfdf26180f617131252a847fdc11","last_reissued_at":"2026-07-05T00:23:49.093519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:49.093519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06707","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:23:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2BGV1ON9LkuG95pid0o+cCZH2XQ0/rLvsyXGhNkVRbg5rUucF2Jyw0dUEaDrf/ETlWmJZUwdi6knvAhT84UDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:59:13.854294Z"},"content_sha256":"081662e1beebc2054deb1fa90d1fa65009dae4b54c584cd2acfbdbb493954a3b","schema_version":"1.0","event_id":"sha256:081662e1beebc2054deb1fa90d1fa65009dae4b54c584cd2acfbdbb493954a3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:L4FBXN6N55RJZNGNIHVLAEPVXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Timo Schick","submitted_at":"2019-04-14T15:26:52Z","abstract_excerpt":"Pretraining deep neural network architectures with a language modeling objective has brought large improvements for many natural language processing tasks. Exemplified by BERT, a recently proposed such architecture, we demonstrate that despite being trained on huge amounts of data, deep language models still struggle to understand rare words. To fix this problem, we adapt Attentive Mimicking, a method that was designed to explicitly learn embeddings for rare words, to deep language models. In order to make this possible, we introduce one-token approximation, a procedure that enables us to use "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06707","kind":"arxiv","version":4},"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/1904.06707/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":"2026-07-05T00:23:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aCIbpM4AWrtpckphJuYugLGbBnAbo+fuvbJ+JS6y152g/rc+5bvhjesVp0t7COcHamLxIpdRy6Ivy0/z+p6DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:59:13.854878Z"},"content_sha256":"cb46632e13cc4058567c15593dafb8af212e1a424a5b7557a9c7fa6a24d10b0d","schema_version":"1.0","event_id":"sha256:cb46632e13cc4058567c15593dafb8af212e1a424a5b7557a9c7fa6a24d10b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4FBXN6N55RJZNGNIHVLAEPVXM/bundle.json","state_url":"https://pith.science/pith/L4FBXN6N55RJZNGNIHVLAEPVXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4FBXN6N55RJZNGNIHVLAEPVXM/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":"2026-08-18T17:59:13Z","links":{"resolver":"https://pith.science/pith/L4FBXN6N55RJZNGNIHVLAEPVXM","bundle":"https://pith.science/pith/L4FBXN6N55RJZNGNIHVLAEPVXM/bundle.json","state":"https://pith.science/pith/L4FBXN6N55RJZNGNIHVLAEPVXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4FBXN6N55RJZNGNIHVLAEPVXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L4FBXN6N55RJZNGNIHVLAEPVXM","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":"2dfba22748926ab901db1fff90ae2d63a6270a82ab0b954380e61d9ed318a4ad","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T15:26:52Z","title_canon_sha256":"4fa27bca99c88720fedd885bd8c3e040a67f102f976a3a3ce406da5f287799a0"},"schema_version":"1.0","source":{"id":"1904.06707","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06707","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06707v4","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06707","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"pith_short_12","alias_value":"L4FBXN6N55RJ","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"pith_short_16","alias_value":"L4FBXN6N55RJZNGN","created_at":"2026-07-05T00:23:49Z"},{"alias_kind":"pith_short_8","alias_value":"L4FBXN6N","created_at":"2026-07-05T00:23:49Z"}],"graph_snapshots":[{"event_id":"sha256:cb46632e13cc4058567c15593dafb8af212e1a424a5b7557a9c7fa6a24d10b0d","target":"graph","created_at":"2026-07-05T00:23:49Z","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/1904.06707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining deep neural network architectures with a language modeling objective has brought large improvements for many natural language processing tasks. Exemplified by BERT, a recently proposed such architecture, we demonstrate that despite being trained on huge amounts of data, deep language models still struggle to understand rare words. To fix this problem, we adapt Attentive Mimicking, a method that was designed to explicitly learn embeddings for rare words, to deep language models. In order to make this possible, we introduce one-token approximation, a procedure that enables us to use ","authors_text":"Hinrich Sch\\\"utze, Timo Schick","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T15:26:52Z","title":"Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06707","kind":"arxiv","version":4},"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":"sha256:081662e1beebc2054deb1fa90d1fa65009dae4b54c584cd2acfbdbb493954a3b","target":"record","created_at":"2026-07-05T00:23:49Z","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":"2dfba22748926ab901db1fff90ae2d63a6270a82ab0b954380e61d9ed318a4ad","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T15:26:52Z","title_canon_sha256":"4fa27bca99c88720fedd885bd8c3e040a67f102f976a3a3ce406da5f287799a0"},"schema_version":"1.0","source":{"id":"1904.06707","kind":"arxiv","version":4}},"canonical_sha256":"5f0a1bb7cdef629cb4cd41eab011f5bb2c22bfdf26180f617131252a847fdc11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f0a1bb7cdef629cb4cd41eab011f5bb2c22bfdf26180f617131252a847fdc11","first_computed_at":"2026-07-05T00:23:49.093519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:49.093519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2zMbEBC4GVsQPCRM+sMyX3T9TYpzyU2unbrEhycRhZVe127CZKzReq4NFiitCWIRsjVQN/xB15bsQR8gvHM7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:49.093944Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06707","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:081662e1beebc2054deb1fa90d1fa65009dae4b54c584cd2acfbdbb493954a3b","sha256:cb46632e13cc4058567c15593dafb8af212e1a424a5b7557a9c7fa6a24d10b0d"],"state_sha256":"10d6ab71360950451e709ec13d9d98df73594fb2023212f127abb1298fe8a112"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/l29czVjUGQ8KhYra5Awdj+ElI9LwA/dAJEoI45jMc9iwuANVwYndn654QKnz7mr7Tx1DLzEHzI5Pq68zMQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:59:13.861225Z","bundle_sha256":"b823714fe06b0cc96e071ea36feb21909addf40906ce423e91f9d445c64a3a50"}}