{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZFLXTETDCD3OE6PU5NUEDO7VCM","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":"a63c147da2c24bc9508b426c051b94d02f298c777177940abe74f5a77224ce93","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-01T02:01:28Z","title_canon_sha256":"86e051ea000b665e4dac6e2a7c86189ea1e7bc6d6b62bf520f9bbe0915c2f904"},"schema_version":"1.0","source":{"id":"2404.00859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00859","created_at":"2026-07-05T08:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00859v2","created_at":"2026-07-05T08:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00859","created_at":"2026-07-05T08:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZFLXTETDCD3O","created_at":"2026-07-05T08:51:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZFLXTETDCD3OE6PU","created_at":"2026-07-05T08:51:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZFLXTETD","created_at":"2026-07-05T08:51:14Z"}],"graph_snapshots":[{"event_id":"sha256:c61365af52d877443ca823d75f901265cabdaaa17552d27923be56037af60931","target":"graph","created_at":"2026-07-05T08:51:14Z","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/2404.00859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Do transformers \"think ahead\" during inference at a given position? It is known transformers prepare information in the hidden states of the forward pass at time step $t$ that is then used in future forward passes $t+\\tau$. We posit two explanations for this phenomenon: pre-caching, in which off-diagonal gradient terms present during training result in the model computing features at $t$ irrelevant to the present inference task but useful for the future, and breadcrumbs, in which features most relevant to time step $t$ are already the same as those that would most benefit inference at time $t+","authors_text":"John X. Morris, Lionel Levine, Wilson Wu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-01T02:01:28Z","title":"Do language models plan ahead for future tokens?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00859","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:bb8cc259010232241b11439986433061bb5c40ce5b9d43e9b1a2278c97d626c7","target":"record","created_at":"2026-07-05T08:51:14Z","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":"a63c147da2c24bc9508b426c051b94d02f298c777177940abe74f5a77224ce93","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-01T02:01:28Z","title_canon_sha256":"86e051ea000b665e4dac6e2a7c86189ea1e7bc6d6b62bf520f9bbe0915c2f904"},"schema_version":"1.0","source":{"id":"2404.00859","kind":"arxiv","version":2}},"canonical_sha256":"c95779926310f6e279f4eb6841bbf5133238072e175098210405c0e73e547b08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c95779926310f6e279f4eb6841bbf5133238072e175098210405c0e73e547b08","first_computed_at":"2026-07-05T08:51:14.733588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:14.733588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wJhmBk6CXSfZ0IecFRRM0Zl25uu7/lcVIvUO/swt5wqZbyrO0pM6omgKvuzmgLy9HTVa2COmKKIUB+6Okt/gAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:14.733976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb8cc259010232241b11439986433061bb5c40ce5b9d43e9b1a2278c97d626c7","sha256:c61365af52d877443ca823d75f901265cabdaaa17552d27923be56037af60931"],"state_sha256":"c638c57f8798693990184df8d29ad2eb8f1950060df823454e82831bc17b4c02"}