{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YN37UFVISQLXYGNTVVIXS6PGOO","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":"a75d6fc00ba08b3f8afc14e2b07868e7bcfbdb23eb6c60d88e817300687eedbb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-15T21:02:48Z","title_canon_sha256":"793f4e08b5050041b5b9233c79d619c10d4ff3b1d8170f50033b41bb72dcab30"},"schema_version":"1.0","source":{"id":"2404.10136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10136","created_at":"2026-07-05T08:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10136v1","created_at":"2026-07-05T08:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10136","created_at":"2026-07-05T08:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"YN37UFVISQLX","created_at":"2026-07-05T08:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"YN37UFVISQLXYGNT","created_at":"2026-07-05T08:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"YN37UFVI","created_at":"2026-07-05T08:08:25Z"}],"graph_snapshots":[{"event_id":"sha256:8a2b8e38fa8747c87e48b7ded2300f214eeb67855c17441908f3ec62fbce815e","target":"graph","created_at":"2026-07-05T08:08:25Z","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/2404.10136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality tradeoffs: here, a small model is invoked for most \"easy\" instances, while a few \"hard\" instances are deferred to the large model. While the principles underpinning cascading are well-studied for classification tasks - with deferral based on predicted class uncertainty favored theoretically and practically - a similar understanding is lacking for generative LM tas","authors_text":"Aditya Krishna Menon, Ankit Singh Rawat, Harikrishna Narasimhan, Neha Gupta, Sanjiv Kumar, Wittawat Jitkrittum","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-15T21:02:48Z","title":"Language Model Cascades: Token-level uncertainty and beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10136","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:ae22a84d0b12c29adec9c32af36100b4fe83c0dfddc98959a906e5df7e10e78e","target":"record","created_at":"2026-07-05T08:08:25Z","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":"a75d6fc00ba08b3f8afc14e2b07868e7bcfbdb23eb6c60d88e817300687eedbb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-15T21:02:48Z","title_canon_sha256":"793f4e08b5050041b5b9233c79d619c10d4ff3b1d8170f50033b41bb72dcab30"},"schema_version":"1.0","source":{"id":"2404.10136","kind":"arxiv","version":1}},"canonical_sha256":"c377fa16a894177c19b3ad517979e67394ef670bcc09f940625dd852e19e2a44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c377fa16a894177c19b3ad517979e67394ef670bcc09f940625dd852e19e2a44","first_computed_at":"2026-07-05T08:08:25.910891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:25.910891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mKAMumKR63LguZhZ8pz695JSj2p5FtUblOMu4VUaSGYoLFPFrhGykwfDd/5nVVyRZO8bllP6AQ7PZBxCkwtaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:25.913835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae22a84d0b12c29adec9c32af36100b4fe83c0dfddc98959a906e5df7e10e78e","sha256:8a2b8e38fa8747c87e48b7ded2300f214eeb67855c17441908f3ec62fbce815e"],"state_sha256":"d8c6956abfbf29d622a516fad35d6aac653c721e259c22f27ee870cba1837b7c"}