{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J6TN5AR2K2WGHXA3DMPYV4YWH3","short_pith_number":"pith:J6TN5AR2","canonical_record":{"source":{"id":"2212.01349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T18:10:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"56c9942700c807e4c52131c909da299051a850b9a69d8d76f4f95924b31df651","abstract_canon_sha256":"d77594ae513987edde9341c73b5a776fd8287a31e3c66683dede979a99f87d57"},"schema_version":"1.0"},"canonical_sha256":"4fa6de823a56ac63dc1b1b1f8af3163ec7b8caccf7e3653f221c6672ac79a502","source":{"kind":"arxiv","id":"2212.01349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01349","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01349v2","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01349","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"J6TN5AR2K2WG","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"J6TN5AR2K2WGHXA3","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"J6TN5AR2","created_at":"2026-07-05T06:14:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J6TN5AR2K2WGHXA3DMPYV4YWH3","target":"record","payload":{"canonical_record":{"source":{"id":"2212.01349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T18:10:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"56c9942700c807e4c52131c909da299051a850b9a69d8d76f4f95924b31df651","abstract_canon_sha256":"d77594ae513987edde9341c73b5a776fd8287a31e3c66683dede979a99f87d57"},"schema_version":"1.0"},"canonical_sha256":"4fa6de823a56ac63dc1b1b1f8af3163ec7b8caccf7e3653f221c6672ac79a502","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:07.023350Z","signature_b64":"Uy8e5hd9gn/aqiho4tZHxQgHjqXv2mKbQdLiW1q7+bm/DPKimD/6+hgY21H+EriJALbiDrvn3b0Qkwv42u6KCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa6de823a56ac63dc1b1b1f8af3163ec7b8caccf7e3653f221c6672ac79a502","last_reissued_at":"2026-07-05T06:14:07.022926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:07.022926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.01349","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":"2026-07-05T06:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LwdxK7I3tav5GrvWcQr7qocE1iSVmSFnJTLr6t/8N7AZDAKxlgOW6ArFPXR8XMkvT+BMOwoTyj6fNMdw5I+DDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:48:57.222740Z"},"content_sha256":"ed4e12ea87837376883d1cdbf4c3adba14801069e9d06e11b9c7af82dbc4d8a1","schema_version":"1.0","event_id":"sha256:ed4e12ea87837376883d1cdbf4c3adba14801069e9d06e11b9c7af82dbc4d8a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J6TN5AR2K2WGHXA3DMPYV4YWH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nonparametric Masked Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Luke Zettlemoyer, Mike Lewis, Sewon Min, Weijia Shi, Wen-tau Yih, Xilun Chen","submitted_at":"2022-12-02T18:10:42Z","abstract_excerpt":"Existing language models (LMs) predict tokens with a softmax over a finite vocabulary, which can make it difficult to predict rare tokens or phrases. We introduce NPM, the first nonparametric masked language model that replaces this softmax with a nonparametric distribution over every phrase in a reference corpus. NPM fills in the [MASK] solely from retrieving a token from a text corpus. We show that NPM can be efficiently trained with a contrastive objective and an in-batch approximation to full corpus retrieval. Zero-shot evaluation on 16 tasks including classification, fact probing and ques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01349","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/2212.01349/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":"2026-07-05T06:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ro38nyKXUNMUXnvvGbyNhoK57gT+aeQVO11/259qLunwe3QiVa0INQhZU8qBr6t5Rz33IY2mEp6yGOY3i5zCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:48:57.223332Z"},"content_sha256":"773bab4ff5f1f0180c45973f02f912cf81b11fa03bc82e2743d92a2f843929b7","schema_version":"1.0","event_id":"sha256:773bab4ff5f1f0180c45973f02f912cf81b11fa03bc82e2743d92a2f843929b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3/bundle.json","state_url":"https://pith.science/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3/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":"2026-08-03T16:48:57Z","links":{"resolver":"https://pith.science/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3","bundle":"https://pith.science/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3/bundle.json","state":"https://pith.science/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J6TN5AR2K2WGHXA3DMPYV4YWH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J6TN5AR2K2WGHXA3DMPYV4YWH3","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":"d77594ae513987edde9341c73b5a776fd8287a31e3c66683dede979a99f87d57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T18:10:42Z","title_canon_sha256":"56c9942700c807e4c52131c909da299051a850b9a69d8d76f4f95924b31df651"},"schema_version":"1.0","source":{"id":"2212.01349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01349","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01349v2","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01349","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"J6TN5AR2K2WG","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"J6TN5AR2K2WGHXA3","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"J6TN5AR2","created_at":"2026-07-05T06:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:773bab4ff5f1f0180c45973f02f912cf81b11fa03bc82e2743d92a2f843929b7","target":"graph","created_at":"2026-07-05T06:14:07Z","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/2212.01349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing language models (LMs) predict tokens with a softmax over a finite vocabulary, which can make it difficult to predict rare tokens or phrases. We introduce NPM, the first nonparametric masked language model that replaces this softmax with a nonparametric distribution over every phrase in a reference corpus. NPM fills in the [MASK] solely from retrieving a token from a text corpus. We show that NPM can be efficiently trained with a contrastive objective and an in-batch approximation to full corpus retrieval. Zero-shot evaluation on 16 tasks including classification, fact probing and ques","authors_text":"Hannaneh Hajishirzi, Luke Zettlemoyer, Mike Lewis, Sewon Min, Weijia Shi, Wen-tau Yih, Xilun Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T18:10:42Z","title":"Nonparametric Masked Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01349","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:ed4e12ea87837376883d1cdbf4c3adba14801069e9d06e11b9c7af82dbc4d8a1","target":"record","created_at":"2026-07-05T06:14:07Z","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":"d77594ae513987edde9341c73b5a776fd8287a31e3c66683dede979a99f87d57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T18:10:42Z","title_canon_sha256":"56c9942700c807e4c52131c909da299051a850b9a69d8d76f4f95924b31df651"},"schema_version":"1.0","source":{"id":"2212.01349","kind":"arxiv","version":2}},"canonical_sha256":"4fa6de823a56ac63dc1b1b1f8af3163ec7b8caccf7e3653f221c6672ac79a502","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fa6de823a56ac63dc1b1b1f8af3163ec7b8caccf7e3653f221c6672ac79a502","first_computed_at":"2026-07-05T06:14:07.022926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:07.022926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uy8e5hd9gn/aqiho4tZHxQgHjqXv2mKbQdLiW1q7+bm/DPKimD/6+hgY21H+EriJALbiDrvn3b0Qkwv42u6KCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:07.023350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.01349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed4e12ea87837376883d1cdbf4c3adba14801069e9d06e11b9c7af82dbc4d8a1","sha256:773bab4ff5f1f0180c45973f02f912cf81b11fa03bc82e2743d92a2f843929b7"],"state_sha256":"0a0ee3f12498a15efa2540ef3408340f70c0f5efa79b81f3dfe158224f707c71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKLZ1wfuesRZEL0sFrzfFCUhCc3//pzXWGO4izZ5Gf5QE+ecg6bLKZdT3B6fb8iSZUrJMjaIatM77EgDjfNMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:48:57.226946Z","bundle_sha256":"777aaede3ccae23dd37ca236e565fe50917d61b3bc52c39265fba2f01a079308"}}