{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NDZ7CBXJAHGCN7E7FF5EFBBIRH","short_pith_number":"pith:NDZ7CBXJ","canonical_record":{"source":{"id":"2411.07279","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-11T18:59:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b80ba4f207a4de0d1067416714bf4ed7a25c3f2b4d5a63c184c06f9680bcf30e","abstract_canon_sha256":"792dd9899d2dd045eb9b26a8f06003c5ac47fa2ba7968117f8ec2e433e6d3264"},"schema_version":"1.0"},"canonical_sha256":"68f3f106e901cc26fc9f297a42842889d3202cc6732653f5d91af4eb9295f3c5","source":{"kind":"arxiv","id":"2411.07279","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NDZ7CBXJAHGCN7E7FF5EFBBIRH","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07279","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-11T18:59:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b80ba4f207a4de0d1067416714bf4ed7a25c3f2b4d5a63c184c06f9680bcf30e","abstract_canon_sha256":"792dd9899d2dd045eb9b26a8f06003c5ac47fa2ba7968117f8ec2e433e6d3264"},"schema_version":"1.0"},"canonical_sha256":"68f3f106e901cc26fc9f297a42842889d3202cc6732653f5d91af4eb9295f3c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:37.864541Z","signature_b64":"F7/UOuvuYa20tvIMIMHdY+UNeCajcheVdMnJ17n9q3Fjt2pf+7ri6JHdn5vHS/dK4QfaCp9lDI7qSMvTXAXgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f3f106e901cc26fc9f297a42842889d3202cc6732653f5d91af4eb9295f3c5","last_reissued_at":"2026-07-05T10:38:37.864053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:37.864053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07279","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":"2026-07-05T10:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ycX+FSYQfu/Gp7axfrybpn/QANhD1QSjyX2lZMRWWa3mlZLlYCnRHVkT3FIuYO5nlQr1ZxgfVA2C2pkqh4TwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:52:04.348203Z"},"content_sha256":"7f5d1bd5f7d0aa71b2909abba0ef19fe41d964cc04bf9c235ddbcc36110c1f4b","schema_version":"1.0","event_id":"sha256:7f5d1bd5f7d0aa71b2909abba0ef19fe41d964cc04bf9c235ddbcc36110c1f4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NDZ7CBXJAHGCN7E7FF5EFBBIRH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Zweiger, Ekin Aky\\\"urek, Han Guo, Jacob Andreas, Jyothish Pari, Linlu Qiu, Mehul Damani, Yoon Kim","submitted_at":"2024-11-11T18:59:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07279","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/2411.07279/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":"2026-07-05T10:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TjcFZ+evpaFyLei/CfOB/I0JfPCk/jYwfbnKun7o+qLdATi41gMQXXlR5WFtAyvsZVtzA+EzKxrvc0obOj/rCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:52:04.348717Z"},"content_sha256":"90cf60a5023c56270abe106014e91b5fe8bd5e98ed6096f1281325084f36f15f","schema_version":"1.0","event_id":"sha256:90cf60a5023c56270abe106014e91b5fe8bd5e98ed6096f1281325084f36f15f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH/bundle.json","state_url":"https://pith.science/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH/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":"2026-08-06T05:52:04Z","links":{"resolver":"https://pith.science/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH","bundle":"https://pith.science/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH/bundle.json","state":"https://pith.science/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDZ7CBXJAHGCN7E7FF5EFBBIRH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OhpqknVVGiGpOBTAcp6T8lGutbGyFcWcmGjcZAlw57EfktinMqYwaWkGvpQEK0jY+Iav19Ku3C6hBXv7EiqFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:52:04.352768Z","bundle_sha256":"f425d6940df47acb5d38ed1ff76c9b568491aa312be8ec49d7c87788f7e645ac"}}