{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XKNODIBJ2LJGWKS2SXX7KWJON2","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":"d91142588680578a815bf590dc4c19690a6d4ca55e4bd41457a9abcde14f1620","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-25T11:13:52Z","title_canon_sha256":"9ba589bec8ff077c48f70dff96808e237179d0d48f04fe2fb83a03ac7660e004"},"schema_version":"1.0","source":{"id":"2607.23153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23153","created_at":"2026-07-28T01:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23153v1","created_at":"2026-07-28T01:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23153","created_at":"2026-07-28T01:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"XKNODIBJ2LJG","created_at":"2026-07-28T01:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"XKNODIBJ2LJGWKS2","created_at":"2026-07-28T01:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"XKNODIBJ","created_at":"2026-07-28T01:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:0066015230201971c199fc1f287d4192e2b4070acfb1e05ec0a9a2437260b33d","target":"graph","created_at":"2026-07-28T01:22:09Z","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/2607.23153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that large language models (LLMs) can iteratively improve their outputs by incorporating generated samples and their corresponding evaluation scores as in-context examples. Despite these empirical findings, the theoretical foundations underlying this phenomenon remain poorly understood. In this paper, we show that score-conditioned In-Context Learning (ICL) admits a structural correspondence to policy gradient optimization. We first provide a constructive proof that self-attention mechanisms can implement reward-weighted aggregation analogous to the REINFORCE algorithm un","authors_text":"Masahiro Kaneko, Timothy Baldwin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-25T11:13:52Z","title":"In-Context Learning as Implicit Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23153","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":"sha256:8b219ea59263e16b523b616ff25e947d96c6917b504cce534749dd66a0a64811","target":"record","created_at":"2026-07-28T01:22:09Z","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":"d91142588680578a815bf590dc4c19690a6d4ca55e4bd41457a9abcde14f1620","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-25T11:13:52Z","title_canon_sha256":"9ba589bec8ff077c48f70dff96808e237179d0d48f04fe2fb83a03ac7660e004"},"schema_version":"1.0","source":{"id":"2607.23153","kind":"arxiv","version":1}},"canonical_sha256":"ba9ae1a029d2d26b2a5a95eff5592e6eaa900f0b39aa1670de70803f98d393dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba9ae1a029d2d26b2a5a95eff5592e6eaa900f0b39aa1670de70803f98d393dc","first_computed_at":"2026-07-28T01:22:09.661809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:09.661809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQHCxFSTi6kWd9LDEKKsqzmw4Ay3XTCIZBpHUgW0dNwaD5Rigw2I6fxBZJGGBMU/3N2FF5skhw56cHOWvjK/DQ==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:09.662687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b219ea59263e16b523b616ff25e947d96c6917b504cce534749dd66a0a64811","sha256:0066015230201971c199fc1f287d4192e2b4070acfb1e05ec0a9a2437260b33d"],"state_sha256":"b7307ebcde81a02e0333a7d029032d78a153d520d34e16d0156ffa4a6d480bc6"}