{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDZ7CBXJAHGCN7E7FF5EFBBIRH","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":"792dd9899d2dd045eb9b26a8f06003c5ac47fa2ba7968117f8ec2e433e6d3264","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-11T18:59:45Z","title_canon_sha256":"b80ba4f207a4de0d1067416714bf4ed7a25c3f2b4d5a63c184c06f9680bcf30e"},"schema_version":"1.0","source":{"id":"2411.07279","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07279","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07279v2","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07279","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"NDZ7CBXJAHGC","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"NDZ7CBXJAHGCN7E7","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"NDZ7CBXJ","created_at":"2026-07-05T10:38:37Z"}],"graph_snapshots":[{"event_id":"sha256:90cf60a5023c56270abe106014e91b5fe8bd5e98ed6096f1281325084f36f15f","target":"graph","created_at":"2026-07-05T10:38:37Z","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/2411.07279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the effectiveness of test-time training (TTT) -- temporarily updating model parameters during inference using a loss derived from input data -- as a mechanism for improving LMs' reasoning and few-shot learning capabilities. On the Abstraction and Reasoning Corpus (ARC), performing TTT with in-context examples yields up to $6\\times$ higher accuracy compared to fine-tuned ba","authors_text":"Adam Zweiger, Ekin Aky\\\"urek, Han Guo, Jacob Andreas, Jyothish Pari, Linlu Qiu, Mehul Damani, Yoon Kim","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-11T18:59:45Z","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07279","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":"sha256:7f5d1bd5f7d0aa71b2909abba0ef19fe41d964cc04bf9c235ddbcc36110c1f4b","target":"record","created_at":"2026-07-05T10:38:37Z","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":"792dd9899d2dd045eb9b26a8f06003c5ac47fa2ba7968117f8ec2e433e6d3264","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-11T18:59:45Z","title_canon_sha256":"b80ba4f207a4de0d1067416714bf4ed7a25c3f2b4d5a63c184c06f9680bcf30e"},"schema_version":"1.0","source":{"id":"2411.07279","kind":"arxiv","version":2}},"canonical_sha256":"68f3f106e901cc26fc9f297a42842889d3202cc6732653f5d91af4eb9295f3c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68f3f106e901cc26fc9f297a42842889d3202cc6732653f5d91af4eb9295f3c5","first_computed_at":"2026-07-05T10:38:37.864053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:37.864053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F7/UOuvuYa20tvIMIMHdY+UNeCajcheVdMnJ17n9q3Fjt2pf+7ri6JHdn5vHS/dK4QfaCp9lDI7qSMvTXAXgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:37.864541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07279","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f5d1bd5f7d0aa71b2909abba0ef19fe41d964cc04bf9c235ddbcc36110c1f4b","sha256:90cf60a5023c56270abe106014e91b5fe8bd5e98ed6096f1281325084f36f15f"],"state_sha256":"7be00f4bf011a79f9c5a70cfce665a899525a25426e9b084c8ab5fce414b4198"}