{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZD56OO7JFXC3PRZ452D2HRASRD","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2607ef46c8932f8baa9dc124dd9d75d893f2056e98c3ec0d6268310463f7381b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T03:57:22Z","title_canon_sha256":"0ba5bf7123c7a5f13182c4c58ce60065149f6ee70f7ce8705173106426b4c498"},"schema_version":"1.0","source":{"id":"2607.17524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17524","created_at":"2026-07-21T01:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17524v1","created_at":"2026-07-21T01:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17524","created_at":"2026-07-21T01:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZD56OO7JFXC3","created_at":"2026-07-21T01:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZD56OO7JFXC3PRZ4","created_at":"2026-07-21T01:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZD56OO7J","created_at":"2026-07-21T01:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:68cc5abada53553c64793b0f9765911917b6b0a06ecb5874f46f8535308f0003","target":"graph","created_at":"2026-07-21T01:21:50Z","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/2607.17524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens. Experiments on document summarization tasks show that TOPL achieves strong out-of-distribution generalization across 11 datasets against a diverse set of sequence-level and token-lev","authors_text":"Deqing Fu, Gustavo Lucas Carvalho, Robin Jia, Zitong Huang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T03:57:22Z","title":"Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17524","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:f1459885d43b55691d8390230b0f58bd5fe2067c43b24521fa01220b821c3f3a","target":"record","created_at":"2026-07-21T01:21:50Z","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":"2607ef46c8932f8baa9dc124dd9d75d893f2056e98c3ec0d6268310463f7381b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T03:57:22Z","title_canon_sha256":"0ba5bf7123c7a5f13182c4c58ce60065149f6ee70f7ce8705173106426b4c498"},"schema_version":"1.0","source":{"id":"2607.17524","kind":"arxiv","version":1}},"canonical_sha256":"c8fbe73be92dc5b7c73cee87a3c41288d3e318ad1a58f5adfb7bb7ef3a40bf78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8fbe73be92dc5b7c73cee87a3c41288d3e318ad1a58f5adfb7bb7ef3a40bf78","first_computed_at":"2026-07-21T01:21:50.462924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:50.462924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u/74CPchmpuWtltyrLYzcvRTZOz16PE+0Zl97Rh7LVKCld3F1tU7SNa2TF5786QomJ+XV2WyxTT65fk0mUWJCA==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:50.463782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1459885d43b55691d8390230b0f58bd5fe2067c43b24521fa01220b821c3f3a","sha256:68cc5abada53553c64793b0f9765911917b6b0a06ecb5874f46f8535308f0003","sha256:21eefe87cf19533141bcf5c7cbf7bc687dcd6eb1d9f1db7d81cc312c127158b4"],"state_sha256":"5ca2bcce8f0e9253dd5616a24b65638262ee8347226838484ac27fc4adad85f1"}