{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6V4RFHPHCLSAUUDWIALJRLR3VD","short_pith_number":"pith:6V4RFHPH","canonical_record":{"source":{"id":"2102.02557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T11:47:03Z","cross_cats_sorted":[],"title_canon_sha256":"801de53e9f6e31415654e9349b182d2c191ed1893d5ad26468ff1b4571f0adde","abstract_canon_sha256":"a6fa20c9be8f72f060f0f41cd2f8fdbdcfed9808f8e575d28483a4e99a2498dd"},"schema_version":"1.0"},"canonical_sha256":"f579129de712e40a5076401698ae3ba8e0ac53fbcceeb80c5bb0c33f23551e4d","source":{"kind":"arxiv","id":"2102.02557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02557","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02557v1","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02557","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"6V4RFHPHCLSA","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"6V4RFHPHCLSAUUDW","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"6V4RFHPH","created_at":"2026-07-05T02:12:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6V4RFHPHCLSAUUDWIALJRLR3VD","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T11:47:03Z","cross_cats_sorted":[],"title_canon_sha256":"801de53e9f6e31415654e9349b182d2c191ed1893d5ad26468ff1b4571f0adde","abstract_canon_sha256":"a6fa20c9be8f72f060f0f41cd2f8fdbdcfed9808f8e575d28483a4e99a2498dd"},"schema_version":"1.0"},"canonical_sha256":"f579129de712e40a5076401698ae3ba8e0ac53fbcceeb80c5bb0c33f23551e4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:49.507782Z","signature_b64":"UsLquLAbcNtWeSYNXUAGgmeWHvT97fVAlWQ3tHdf4mWGL124EwqJh3NDJhMtEQ2o3Rypl5MJOrKLN81gJSItDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f579129de712e40a5076401698ae3ba8e0ac53fbcceeb80c5bb0c33f23551e4d","last_reissued_at":"2026-07-05T02:12:49.507332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:49.507332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02557","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHWkAYMK9lAWo85KWc3r2nkseNEgcksh/nArJn9HnW48PWpdlS42QGP0vwbMHFDJa7JQdvEiUeu6m2yTvUanAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:51:11.166591Z"},"content_sha256":"b3dfdffd81a2ffa9216ff2d243d8498c4d84483741ad99146f85ce4b76dcc2e8","schema_version":"1.0","event_id":"sha256:b3dfdffd81a2ffa9216ff2d243d8498c4d84483741ad99146f85ce4b76dcc2e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6V4RFHPHCLSAUUDWIALJRLR3VD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Semiparametric Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cyprien de Masson d'Autume, Dani Yogatama, Lingpeng Kong","submitted_at":"2021-02-04T11:47:03Z","abstract_excerpt":"We present a language model that combines a large parametric neural network (i.e., a transformer) with a non-parametric episodic memory component in an integrated architecture. Our model uses extended short-term context by caching local hidden states -- similar to transformer-XL -- and global long-term memory by retrieving a set of nearest neighbor tokens at each timestep. We design a gating function to adaptively combine multiple information sources to make a prediction. This mechanism allows the model to use either local context, short-term memory, or long-term memory (or any combination of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02557","kind":"arxiv","version":1},"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/2102.02557/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":"2026-07-05T02:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0CZE539/5PEor45LDbw26WnJs1OfhpXFuFO75Cjv/cCLPeNx/01dOZPGaWKammKuvTcF9g2lcayxOQf9R3A+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:51:11.167121Z"},"content_sha256":"431bd955fb8f7936bff488220b6e808c9e1a0b5b2d1834c17d35be5554c5c244","schema_version":"1.0","event_id":"sha256:431bd955fb8f7936bff488220b6e808c9e1a0b5b2d1834c17d35be5554c5c244"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6V4RFHPHCLSAUUDWIALJRLR3VD/bundle.json","state_url":"https://pith.science/pith/6V4RFHPHCLSAUUDWIALJRLR3VD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6V4RFHPHCLSAUUDWIALJRLR3VD/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":"2026-08-05T04:51:11Z","links":{"resolver":"https://pith.science/pith/6V4RFHPHCLSAUUDWIALJRLR3VD","bundle":"https://pith.science/pith/6V4RFHPHCLSAUUDWIALJRLR3VD/bundle.json","state":"https://pith.science/pith/6V4RFHPHCLSAUUDWIALJRLR3VD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6V4RFHPHCLSAUUDWIALJRLR3VD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6V4RFHPHCLSAUUDWIALJRLR3VD","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":"a6fa20c9be8f72f060f0f41cd2f8fdbdcfed9808f8e575d28483a4e99a2498dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T11:47:03Z","title_canon_sha256":"801de53e9f6e31415654e9349b182d2c191ed1893d5ad26468ff1b4571f0adde"},"schema_version":"1.0","source":{"id":"2102.02557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02557","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02557v1","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02557","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"6V4RFHPHCLSA","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"6V4RFHPHCLSAUUDW","created_at":"2026-07-05T02:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"6V4RFHPH","created_at":"2026-07-05T02:12:49Z"}],"graph_snapshots":[{"event_id":"sha256:431bd955fb8f7936bff488220b6e808c9e1a0b5b2d1834c17d35be5554c5c244","target":"graph","created_at":"2026-07-05T02:12:49Z","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/2102.02557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a language model that combines a large parametric neural network (i.e., a transformer) with a non-parametric episodic memory component in an integrated architecture. Our model uses extended short-term context by caching local hidden states -- similar to transformer-XL -- and global long-term memory by retrieving a set of nearest neighbor tokens at each timestep. We design a gating function to adaptively combine multiple information sources to make a prediction. This mechanism allows the model to use either local context, short-term memory, or long-term memory (or any combination of ","authors_text":"Cyprien de Masson d'Autume, Dani Yogatama, Lingpeng Kong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T11:47:03Z","title":"Adaptive Semiparametric Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02557","kind":"arxiv","version":1},"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:b3dfdffd81a2ffa9216ff2d243d8498c4d84483741ad99146f85ce4b76dcc2e8","target":"record","created_at":"2026-07-05T02:12:49Z","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":"a6fa20c9be8f72f060f0f41cd2f8fdbdcfed9808f8e575d28483a4e99a2498dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T11:47:03Z","title_canon_sha256":"801de53e9f6e31415654e9349b182d2c191ed1893d5ad26468ff1b4571f0adde"},"schema_version":"1.0","source":{"id":"2102.02557","kind":"arxiv","version":1}},"canonical_sha256":"f579129de712e40a5076401698ae3ba8e0ac53fbcceeb80c5bb0c33f23551e4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f579129de712e40a5076401698ae3ba8e0ac53fbcceeb80c5bb0c33f23551e4d","first_computed_at":"2026-07-05T02:12:49.507332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:49.507332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UsLquLAbcNtWeSYNXUAGgmeWHvT97fVAlWQ3tHdf4mWGL124EwqJh3NDJhMtEQ2o3Rypl5MJOrKLN81gJSItDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:49.507782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3dfdffd81a2ffa9216ff2d243d8498c4d84483741ad99146f85ce4b76dcc2e8","sha256:431bd955fb8f7936bff488220b6e808c9e1a0b5b2d1834c17d35be5554c5c244"],"state_sha256":"e69c6bd2e731aeb93a410225cfbc79c5dc3b1cb1be0d444b1102c3370656183f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIfRNigKSHSta2Bz9e20SJPeD43uYEvjiPrkCRtOgfED/cHQuald/8UE+tX3yzAkB8m1MlQmhVTErqQjVwVMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:51:11.172247Z","bundle_sha256":"909335bceeee3cf04df08a7be176d878bbb21a00e650c9422701a77a565444de"}}