{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:24VFHJXWYFJGPGRHD7WHIM4UIB","short_pith_number":"pith:24VFHJXW","canonical_record":{"source":{"id":"2605.18592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:06:27Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5f5160128c23451af8e5a7238aafa8d282e216bbc320668e1769f4c09f032e18","abstract_canon_sha256":"4840dde5ffb95a48003d6fdd4ba3fac5f8c0d1560d48a9b392a2ebdc8298ffb7"},"schema_version":"1.0"},"canonical_sha256":"d72a53a6f6c152679a271fec7433944073be2a23916c5a6fe0d3955347375244","source":{"kind":"arxiv","id":"2605.18592","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18592","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18592v1","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18592","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"24VFHJXWYFJG","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"24VFHJXWYFJGPGRH","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"24VFHJXW","created_at":"2026-05-20T00:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:24VFHJXWYFJGPGRHD7WHIM4UIB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:06:27Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5f5160128c23451af8e5a7238aafa8d282e216bbc320668e1769f4c09f032e18","abstract_canon_sha256":"4840dde5ffb95a48003d6fdd4ba3fac5f8c0d1560d48a9b392a2ebdc8298ffb7"},"schema_version":"1.0"},"canonical_sha256":"d72a53a6f6c152679a271fec7433944073be2a23916c5a6fe0d3955347375244","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:09.773887Z","signature_b64":"IXt5Pe4xpxhE2K1UvW8U/b5+Ejb9AZELtTWHTM271virBCZeJT0hJjLuWxztdWT2eO4jLFHLEqy9nqKu+YGfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72a53a6f6c152679a271fec7433944073be2a23916c5a6fe0d3955347375244","last_reissued_at":"2026-05-20T00:06:09.772949Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:09.772949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18592","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FbADElfgRlghus4UygIfcytp0a5z2yK8IrRcQFzR3UEMSAww20U3gSvHfjpfYvVepGMyim9FUQV2zE7cRJUsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:02:31.852224Z"},"content_sha256":"76c6b4de493f44fbfc624cd7e196a4da0059a8ae12b0d4ca8aeaf5bf8a62fc46","schema_version":"1.0","event_id":"sha256:76c6b4de493f44fbfc624cd7e196a4da0059a8ae12b0d4ca8aeaf5bf8a62fc46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:24VFHJXWYFJGPGRHD7WHIM4UIB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Gang Wu, Kun Wan, Peilin Wu, Wentian Zhao, Xinlu Zhang, Xinya Du, Zhiyu Chen","submitted_at":"2026-05-18T16:06:27Z","abstract_excerpt":"Rubric-based reward shaping is an effective method for fine-tuning LLMs via RL, where structured rubrics decompose standard outcome rewards into multiple dimensions to provide richer reward signals. Recent works make the rubrics adaptive based on local signals such as the rollouts from the current step or pairwise comparisons. However, these methods discard the diagnostics produced during evaluation after immediate use and prevent the long-term accumulation and strategic reuse of evaluation knowledge. This forces the system to re-derive evaluation principles from scratch, limits its ability to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18592","kind":"arxiv","version":1},"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/2605.18592/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.281305Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"62d2508f9cc172e5dbd0b467f87ed15825863b984bf3b2156335d5ebe30c6e2b"},"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":"2026-05-20T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gdLY7dSJgLFj6HhynXGW6x2PUJNxq0Mx0QevoFcSIDRdbzew3GO0rVPYmsUJFRoe1WrrZOzPbv+1LMOeyAYjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:02:31.852972Z"},"content_sha256":"39a9697693c5a36acc5964c3c7f1000b41bcea12b835483e078b162d7466cf9a","schema_version":"1.0","event_id":"sha256:39a9697693c5a36acc5964c3c7f1000b41bcea12b835483e078b162d7466cf9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24VFHJXWYFJGPGRHD7WHIM4UIB/bundle.json","state_url":"https://pith.science/pith/24VFHJXWYFJGPGRHD7WHIM4UIB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24VFHJXWYFJGPGRHD7WHIM4UIB/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":"2026-05-26T13:02:31Z","links":{"resolver":"https://pith.science/pith/24VFHJXWYFJGPGRHD7WHIM4UIB","bundle":"https://pith.science/pith/24VFHJXWYFJGPGRHD7WHIM4UIB/bundle.json","state":"https://pith.science/pith/24VFHJXWYFJGPGRHD7WHIM4UIB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24VFHJXWYFJGPGRHD7WHIM4UIB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:24VFHJXWYFJGPGRHD7WHIM4UIB","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":"4840dde5ffb95a48003d6fdd4ba3fac5f8c0d1560d48a9b392a2ebdc8298ffb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:06:27Z","title_canon_sha256":"5f5160128c23451af8e5a7238aafa8d282e216bbc320668e1769f4c09f032e18"},"schema_version":"1.0","source":{"id":"2605.18592","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18592","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18592v1","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18592","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"24VFHJXWYFJG","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"24VFHJXWYFJGPGRH","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"24VFHJXW","created_at":"2026-05-20T00:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:39a9697693c5a36acc5964c3c7f1000b41bcea12b835483e078b162d7466cf9a","target":"graph","created_at":"2026-05-20T00:06:09Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.281305Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18592/integrity.json","findings":[],"snapshot_sha256":"62d2508f9cc172e5dbd0b467f87ed15825863b984bf3b2156335d5ebe30c6e2b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubric-based reward shaping is an effective method for fine-tuning LLMs via RL, where structured rubrics decompose standard outcome rewards into multiple dimensions to provide richer reward signals. Recent works make the rubrics adaptive based on local signals such as the rollouts from the current step or pairwise comparisons. However, these methods discard the diagnostics produced during evaluation after immediate use and prevent the long-term accumulation and strategic reuse of evaluation knowledge. This forces the system to re-derive evaluation principles from scratch, limits its ability to","authors_text":"Gang Wu, Kun Wan, Peilin Wu, Wentian Zhao, Xinlu Zhang, Xinya Du, Zhiyu Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:06:27Z","title":"AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18592","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":"sha256:76c6b4de493f44fbfc624cd7e196a4da0059a8ae12b0d4ca8aeaf5bf8a62fc46","target":"record","created_at":"2026-05-20T00:06:09Z","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":"4840dde5ffb95a48003d6fdd4ba3fac5f8c0d1560d48a9b392a2ebdc8298ffb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:06:27Z","title_canon_sha256":"5f5160128c23451af8e5a7238aafa8d282e216bbc320668e1769f4c09f032e18"},"schema_version":"1.0","source":{"id":"2605.18592","kind":"arxiv","version":1}},"canonical_sha256":"d72a53a6f6c152679a271fec7433944073be2a23916c5a6fe0d3955347375244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d72a53a6f6c152679a271fec7433944073be2a23916c5a6fe0d3955347375244","first_computed_at":"2026-05-20T00:06:09.772949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:09.772949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IXt5Pe4xpxhE2K1UvW8U/b5+Ejb9AZELtTWHTM271virBCZeJT0hJjLuWxztdWT2eO4jLFHLEqy9nqKu+YGfAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:09.773887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18592","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76c6b4de493f44fbfc624cd7e196a4da0059a8ae12b0d4ca8aeaf5bf8a62fc46","sha256:39a9697693c5a36acc5964c3c7f1000b41bcea12b835483e078b162d7466cf9a"],"state_sha256":"47971bf23aceb4037f76bb5b5b88aaf4adc9cc5e5a6531b75b5c9ab56147f42c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFdv4opk2OlumOL+Fhg8ZvKJ+s+LeWWSRinNaDHFuMo2+xHt2WbEWfHvXQXrMTq9F5IieFoPK1oodVLMR4BmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:02:31.856660Z","bundle_sha256":"3873644bf1c48cadd6bb8715909e448844e593b259d40d722f8b672fc4b64aa9"}}