{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7XHN7ARINL6YNGG6C7VTLF75ID","short_pith_number":"pith:7XHN7ARI","canonical_record":{"source":{"id":"2505.02666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:15:02Z","cross_cats_sorted":[],"title_canon_sha256":"2c4b9bf7f5cf63db83e174637c6887b4ecfd1489749a990e562f2a6b5b418740","abstract_canon_sha256":"e78d313e3d859960b696a86422e60bd9355e907eaf0ae5c71ea945c81f569294"},"schema_version":"1.0"},"canonical_sha256":"fdcedf82286afd8698de17eb3597fd40e747105a630ed6e5462f6a07fbe648de","source":{"kind":"arxiv","id":"2505.02666","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7XHN7ARINL6YNGG6C7VTLF75ID","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:15:02Z","cross_cats_sorted":[],"title_canon_sha256":"2c4b9bf7f5cf63db83e174637c6887b4ecfd1489749a990e562f2a6b5b418740","abstract_canon_sha256":"e78d313e3d859960b696a86422e60bd9355e907eaf0ae5c71ea945c81f569294"},"schema_version":"1.0"},"canonical_sha256":"fdcedf82286afd8698de17eb3597fd40e747105a630ed6e5462f6a07fbe648de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:26.474955Z","signature_b64":"+76nXRb72ZYf/VodxEFXZTThmWsBSA+KYQOegXutgZuRd03BwN95FHDXQD+ML6RWJI567ptNaDWNbuX3WDbFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdcedf82286afd8698de17eb3597fd40e747105a630ed6e5462f6a07fbe648de","last_reissued_at":"2026-07-05T12:03:26.474453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:26.474453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02666","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z17UDIrS0AoGgROtOw5WbHaPJkHdI6/Jz70hsDDtAzEXnfB2q+tAczYL6mCmb5Fh/mRLxyjjIEV4JI4lDhr0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:02:05.399605Z"},"content_sha256":"2bf7378c9d8c4546a67727f95bc6b98c1fd4cac75fffaefff65da5e55a585405","schema_version":"1.0","event_id":"sha256:2bf7378c9d8c4546a67727f95bc6b98c1fd4cac75fffaefff65da5e55a585405"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7XHN7ARINL6YNGG6C7VTLF75ID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian Yang, Mark Dras, Miaomiao Ji, Shoujin Wang, Usman Naseem, Yanqiu Wu, Zhibin Wu","submitted_at":"2025-05-05T14:15:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02666","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.02666/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6vO6gMyfubKO3bKPBVlLGkpi0KxNfT4aNdK4laqRZOCVCbeXT4e6PK+QcGP11gr9HwyOfHyEwrYRqztWW0LZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:02:05.400150Z"},"content_sha256":"c6d685dfe669d13f787e95556cca78abd16d13cc306f9701306df8cdc1d5dcb3","schema_version":"1.0","event_id":"sha256:c6d685dfe669d13f787e95556cca78abd16d13cc306f9701306df8cdc1d5dcb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XHN7ARINL6YNGG6C7VTLF75ID/bundle.json","state_url":"https://pith.science/pith/7XHN7ARINL6YNGG6C7VTLF75ID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XHN7ARINL6YNGG6C7VTLF75ID/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T03:02:05Z","links":{"resolver":"https://pith.science/pith/7XHN7ARINL6YNGG6C7VTLF75ID","bundle":"https://pith.science/pith/7XHN7ARINL6YNGG6C7VTLF75ID/bundle.json","state":"https://pith.science/pith/7XHN7ARINL6YNGG6C7VTLF75ID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XHN7ARINL6YNGG6C7VTLF75ID/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4sMRkfItFdktbHNL1Ja07ol34N48u8cGg8G34ewjjlut58M0GBPnq+pTerwHGShX6Qm4LYtpJFCZFULcItrpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:02:05.404008Z","bundle_sha256":"25ab6aa0686a0a1b3a8dceb305812c4bd823f64090f73fdf86d537b6bc5e518e"}}