{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7XHN7ARINL6YNGG6C7VTLF75ID","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":"e78d313e3d859960b696a86422e60bd9355e907eaf0ae5c71ea945c81f569294","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:15:02Z","title_canon_sha256":"2c4b9bf7f5cf63db83e174637c6887b4ecfd1489749a990e562f2a6b5b418740"},"schema_version":"1.0","source":{"id":"2505.02666","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02666","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02666v2","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02666","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"7XHN7ARINL6Y","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"7XHN7ARINL6YNGG6","created_at":"2026-07-05T12:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"7XHN7ARI","created_at":"2026-07-05T12:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:c6d685dfe669d13f787e95556cca78abd16d13cc306f9701306df8cdc1d5dcb3","target":"graph","created_at":"2026-07-05T12:03:26Z","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/2505.02666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward design plays a pivotal role in aligning large language models (LLMs) with human values, serving as the bridge between feedback signals and model optimization. This survey provides a structured organization of reward modeling and addresses three key aspects: mathematical formulation, construction practices, and interaction with optimization paradigms. Building on this, it develops a macro-level taxonomy that characterizes reward mechanisms along complementary dimensions, thereby offering both conceptual clarity and practical guidance for alignment research. The progression of LLM alignme","authors_text":"Jian Yang, Mark Dras, Miaomiao Ji, Shoujin Wang, Usman Naseem, Yanqiu Wu, Zhibin Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:15:02Z","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02666","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":"sha256:2bf7378c9d8c4546a67727f95bc6b98c1fd4cac75fffaefff65da5e55a585405","target":"record","created_at":"2026-07-05T12:03:26Z","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":"e78d313e3d859960b696a86422e60bd9355e907eaf0ae5c71ea945c81f569294","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:15:02Z","title_canon_sha256":"2c4b9bf7f5cf63db83e174637c6887b4ecfd1489749a990e562f2a6b5b418740"},"schema_version":"1.0","source":{"id":"2505.02666","kind":"arxiv","version":2}},"canonical_sha256":"fdcedf82286afd8698de17eb3597fd40e747105a630ed6e5462f6a07fbe648de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdcedf82286afd8698de17eb3597fd40e747105a630ed6e5462f6a07fbe648de","first_computed_at":"2026-07-05T12:03:26.474453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:26.474453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+76nXRb72ZYf/VodxEFXZTThmWsBSA+KYQOegXutgZuRd03BwN95FHDXQD+ML6RWJI567ptNaDWNbuX3WDbFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:26.474955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02666","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bf7378c9d8c4546a67727f95bc6b98c1fd4cac75fffaefff65da5e55a585405","sha256:c6d685dfe669d13f787e95556cca78abd16d13cc306f9701306df8cdc1d5dcb3"],"state_sha256":"a87194a3102f0ec930602c9e646dcaaaf2432f4b846257078dea8adadd7ffac3"}