{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EW4IDPV7DARZ623I5DIXLAXFLH","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":"2781174c9bbd98ecb02fa44c23a12901c6f825cfc0e38f62191a8dbd4edbe684","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T14:19:49Z","title_canon_sha256":"8baa98ca833925d32d95a6f837ff1e66b09e0ba00edadd9fa45e159395adaf53"},"schema_version":"1.0","source":{"id":"2204.05832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05832","created_at":"2026-07-05T04:14:02Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05832v1","created_at":"2026-07-05T04:14:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05832","created_at":"2026-07-05T04:14:02Z"},{"alias_kind":"pith_short_12","alias_value":"EW4IDPV7DARZ","created_at":"2026-07-05T04:14:02Z"},{"alias_kind":"pith_short_16","alias_value":"EW4IDPV7DARZ623I","created_at":"2026-07-05T04:14:02Z"},{"alias_kind":"pith_short_8","alias_value":"EW4IDPV7","created_at":"2026-07-05T04:14:02Z"}],"graph_snapshots":[{"event_id":"sha256:9740281089ced53f4dabe915678b340753e15203f1fb8c7aa3d95c93fc83e54c","target":"graph","created_at":"2026-07-05T04:14:02Z","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/2204.05832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly trained on. However, the architectures and pretraining objectives used across state-of-the-art models differ significantly, and there has been limited systematic comparison of these factors. In this work, we present a large-scale evaluation of modeling choices and their impact on zero-shot generalization. In particular, we focus on text-to-text models and experiment with three model architectures (causal/non-causal decoder","authors_text":"Adam Roberts, Colin Raffel, Daniel Hesslow, Hyung Won Chung, Iz Beltagy, Julien Launay, Teven Le Scao, Thomas Wang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T14:19:49Z","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05832","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:b05b71c92f0d20affd1bcd1744aed50f62075788e07bdc876c24148d6c771d11","target":"record","created_at":"2026-07-05T04:14:02Z","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":"2781174c9bbd98ecb02fa44c23a12901c6f825cfc0e38f62191a8dbd4edbe684","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T14:19:49Z","title_canon_sha256":"8baa98ca833925d32d95a6f837ff1e66b09e0ba00edadd9fa45e159395adaf53"},"schema_version":"1.0","source":{"id":"2204.05832","kind":"arxiv","version":1}},"canonical_sha256":"25b881bebf18239f6b68e8d17582e559d58ad31ea028bb6c7022bc2d27731c82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25b881bebf18239f6b68e8d17582e559d58ad31ea028bb6c7022bc2d27731c82","first_computed_at":"2026-07-05T04:14:02.871571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:02.871571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dfPze/zPx0px5QB1mSxi8PEYFkMlSUatdFTorv4pI58XgaNrr5fbL7KeqjXask3DwGGRGCyrv+eeK0Yajs13Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:02.872033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b05b71c92f0d20affd1bcd1744aed50f62075788e07bdc876c24148d6c771d11","sha256:9740281089ced53f4dabe915678b340753e15203f1fb8c7aa3d95c93fc83e54c"],"state_sha256":"9052b54a7639fe22e99ae46fe963f656ed04efdf50829b705303e8af00070fca"}