{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EUBTURJBWCDKBJ4Z4TXGUOJCDO","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":"15c4e6ed20ef6f0cf2efa89aad5c764fd1fe4912623bdb45825794bcc2bb24bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:33:49Z","title_canon_sha256":"6162642b0c937f7f635d360a7d0dc0a4bb76e22a4c35dd038a4a67f619943b11"},"schema_version":"1.0","source":{"id":"2505.02686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02686","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02686v2","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02686","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"EUBTURJBWCDK","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"EUBTURJBWCDKBJ4Z","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"EUBTURJB","created_at":"2026-07-05T11:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:876c78d17ba290761b7346e31b8d09b7f0d0364a0628e5e4276e57e045dc9849","target":"graph","created_at":"2026-07-05T11:20:38Z","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/2505.02686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent developments in Large Language Models (LLMs) have shifted from pre-training scaling to post-training and test-time scaling. Across these developments, a key unified paradigm has arisen: Learning from Rewards, where reward signals act as the guiding stars to steer LLM behavior. It has underpinned a wide range of prevalent techniques, such as reinforcement learning (RLHF, RLAIF, DPO, and GRPO), reward-guided decoding, and post-hoc correction. Crucially, this paradigm enables the transition from passive learning from static data to active learning from dynamic feedback. This endows LLMs wi","authors_text":"Xiaobao Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:33:49Z","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02686","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":"sha256:497f5855ce3f5d18e6641119e69cc8629985b66f35388c9f9a827f4cf0516f86","target":"record","created_at":"2026-07-05T11:20:38Z","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":"15c4e6ed20ef6f0cf2efa89aad5c764fd1fe4912623bdb45825794bcc2bb24bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:33:49Z","title_canon_sha256":"6162642b0c937f7f635d360a7d0dc0a4bb76e22a4c35dd038a4a67f619943b11"},"schema_version":"1.0","source":{"id":"2505.02686","kind":"arxiv","version":2}},"canonical_sha256":"25033a4521b086a0a799e4ee6a39221b8fd47b217ad6538afdc5f97ee11fea84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25033a4521b086a0a799e4ee6a39221b8fd47b217ad6538afdc5f97ee11fea84","first_computed_at":"2026-07-05T11:20:38.265912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:38.265912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EuUGD0x/CYASqJv+mh6AfV7UIhF4DSvdQjsSHD/BK/jZfws29+SP4K21Ns5X1fyWukJQwHLxZY6nxC36h5FJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:38.266410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:497f5855ce3f5d18e6641119e69cc8629985b66f35388c9f9a827f4cf0516f86","sha256:876c78d17ba290761b7346e31b8d09b7f0d0364a0628e5e4276e57e045dc9849"],"state_sha256":"6b489282ae172f91ef4f59326c233e52a92635194e8cb580e8a7d024c1c25d9e"}