{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H5K66YRUND4NB5C7TAZ54ALQHF","short_pith_number":"pith:H5K66YRU","canonical_record":{"source":{"id":"2102.01951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-03T09:01:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e15d4262927796a1ccebc26a003f564feb2da4415df9c15ff8276e271f8c7faa","abstract_canon_sha256":"55f59b16efbb1c43dd9c1f7c76ce43f27418382a51675c0366af2c1a69b2e111"},"schema_version":"1.0"},"canonical_sha256":"3f55ef623468f8d0f45f9833de0170394a4ba2c45ffb446b8dde4d514eb9a1a2","source":{"kind":"arxiv","id":"2102.01951","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01951","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01951v2","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01951","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"pith_short_12","alias_value":"H5K66YRUND4N","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"pith_short_16","alias_value":"H5K66YRUND4NB5C7","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"pith_short_8","alias_value":"H5K66YRU","created_at":"2026-07-05T03:25:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H5K66YRUND4NB5C7TAZ54ALQHF","target":"record","payload":{"canonical_record":{"source":{"id":"2102.01951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-03T09:01:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e15d4262927796a1ccebc26a003f564feb2da4415df9c15ff8276e271f8c7faa","abstract_canon_sha256":"55f59b16efbb1c43dd9c1f7c76ce43f27418382a51675c0366af2c1a69b2e111"},"schema_version":"1.0"},"canonical_sha256":"3f55ef623468f8d0f45f9833de0170394a4ba2c45ffb446b8dde4d514eb9a1a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:50.235688Z","signature_b64":"D545WhFF1+sNEdr2owXU+i/n4PKJ9cAMuIIQuH2NPQTfNudm1lzrlbyVco/qeuoFPblP0O6yAYw3lHjA5GkpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f55ef623468f8d0f45f9833de0170394a4ba2c45ffb446b8dde4d514eb9a1a2","last_reissued_at":"2026-07-05T03:25:50.235260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:50.235260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.01951","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":"2026-07-05T03:25:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cv6SSuyozUyirwKy4TQPp9U0i7rwV7YGVu3zIlflPFS4R4U05VpCtjuPL+PN6XCjQITI1riqHu0Vueapw4eiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:21:49.894592Z"},"content_sha256":"47c46d3a4beaa1906bf3b7f74094dc098a2b4f09e37e49eab596f240e208c377","schema_version":"1.0","event_id":"sha256:47c46d3a4beaa1906bf3b7f74094dc098a2b4f09e37e49eab596f240e208c377"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H5K66YRUND4NB5C7TAZ54ALQHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Liska, Adhiguna Kuncoro, Angeliki Lazaridou, Cyprien de Masson d'Autume, Dani Yogatama, Devang Agrawal, Elena Gribovskaya, Kris Cao, Mai Gimenez, Phil Blunsom, Sebastian Ruder, Susannah Young, Tayfun Terzi, Tomas Kocisky","submitted_at":"2021-02-03T09:01:49Z","abstract_excerpt":"Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling paradigm, which trains and evaluates models on utterances from overlapping time periods. Despite impressive recent progress, we demonstrate that Transformer-XL language models perform worse in the realistic setup of predicting future utterances from beyond their training period, and that model performance becomes increasingly worse with time. We find that, while increasi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01951","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/2102.01951/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":"2026-07-05T03:25:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kn3zWkFLV0M6bav5sYnJR9NEppinc/4t6eAWd83rS2txtpxGJLg8fiQ0M2KdDxfo52dhxJ9DJHYSrhndIIVmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:21:49.895123Z"},"content_sha256":"55a05dc24b0b19ae7bd68085b928f202805a568442ac536f04fdbd0010512191","schema_version":"1.0","event_id":"sha256:55a05dc24b0b19ae7bd68085b928f202805a568442ac536f04fdbd0010512191"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5K66YRUND4NB5C7TAZ54ALQHF/bundle.json","state_url":"https://pith.science/pith/H5K66YRUND4NB5C7TAZ54ALQHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5K66YRUND4NB5C7TAZ54ALQHF/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":"2026-08-05T01:21:49Z","links":{"resolver":"https://pith.science/pith/H5K66YRUND4NB5C7TAZ54ALQHF","bundle":"https://pith.science/pith/H5K66YRUND4NB5C7TAZ54ALQHF/bundle.json","state":"https://pith.science/pith/H5K66YRUND4NB5C7TAZ54ALQHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5K66YRUND4NB5C7TAZ54ALQHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H5K66YRUND4NB5C7TAZ54ALQHF","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":"55f59b16efbb1c43dd9c1f7c76ce43f27418382a51675c0366af2c1a69b2e111","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-03T09:01:49Z","title_canon_sha256":"e15d4262927796a1ccebc26a003f564feb2da4415df9c15ff8276e271f8c7faa"},"schema_version":"1.0","source":{"id":"2102.01951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01951","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01951v2","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01951","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"pith_short_12","alias_value":"H5K66YRUND4N","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"pith_short_16","alias_value":"H5K66YRUND4NB5C7","created_at":"2026-07-05T03:25:50Z"},{"alias_kind":"pith_short_8","alias_value":"H5K66YRU","created_at":"2026-07-05T03:25:50Z"}],"graph_snapshots":[{"event_id":"sha256:55a05dc24b0b19ae7bd68085b928f202805a568442ac536f04fdbd0010512191","target":"graph","created_at":"2026-07-05T03:25:50Z","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/2102.01951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling paradigm, which trains and evaluates models on utterances from overlapping time periods. Despite impressive recent progress, we demonstrate that Transformer-XL language models perform worse in the realistic setup of predicting future utterances from beyond their training period, and that model performance becomes increasingly worse with time. We find that, while increasi","authors_text":"Adam Liska, Adhiguna Kuncoro, Angeliki Lazaridou, Cyprien de Masson d'Autume, Dani Yogatama, Devang Agrawal, Elena Gribovskaya, Kris Cao, Mai Gimenez, Phil Blunsom, Sebastian Ruder, Susannah Young, Tayfun Terzi, Tomas Kocisky","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-03T09:01:49Z","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01951","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":"sha256:47c46d3a4beaa1906bf3b7f74094dc098a2b4f09e37e49eab596f240e208c377","target":"record","created_at":"2026-07-05T03:25:50Z","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":"55f59b16efbb1c43dd9c1f7c76ce43f27418382a51675c0366af2c1a69b2e111","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-03T09:01:49Z","title_canon_sha256":"e15d4262927796a1ccebc26a003f564feb2da4415df9c15ff8276e271f8c7faa"},"schema_version":"1.0","source":{"id":"2102.01951","kind":"arxiv","version":2}},"canonical_sha256":"3f55ef623468f8d0f45f9833de0170394a4ba2c45ffb446b8dde4d514eb9a1a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f55ef623468f8d0f45f9833de0170394a4ba2c45ffb446b8dde4d514eb9a1a2","first_computed_at":"2026-07-05T03:25:50.235260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:50.235260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D545WhFF1+sNEdr2owXU+i/n4PKJ9cAMuIIQuH2NPQTfNudm1lzrlbyVco/qeuoFPblP0O6yAYw3lHjA5GkpDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:50.235688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47c46d3a4beaa1906bf3b7f74094dc098a2b4f09e37e49eab596f240e208c377","sha256:55a05dc24b0b19ae7bd68085b928f202805a568442ac536f04fdbd0010512191"],"state_sha256":"56f81f1a9a796714abcff9ad62b3fda9bc6d072e9b965db225baf2d7aa559053"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FpfCc+97YffpvlHGkpGOoErwLswhA8oUdTE+YwkFzlxxM/tUmSn2JcWZC//O1XOKRGijsGauCH5Ju+zkq0ApDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:21:49.898685Z","bundle_sha256":"33c4fb14e759d37bd9061827a87213ad686bc90b796c9b8841b54c7b19b85e0a"}}