{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LZWWCXRHBPWFLSO26ABVQPUTQB","short_pith_number":"pith:LZWWCXRH","canonical_record":{"source":{"id":"2501.15595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T16:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"dba912f7eda47201d7efb00edbc153d65c8a952391523a9eabe482d0b820a7ef","abstract_canon_sha256":"38b6f73fe8651e02d9ba26676469b738d576cdcd980b6747f25a7e278fec2e8e"},"schema_version":"1.0"},"canonical_sha256":"5e6d615e270bec55c9daf003583e9380655a87aaf0786cb278b2623333006e1e","source":{"kind":"arxiv","id":"2501.15595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15595","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15595v1","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15595","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"LZWWCXRHBPWF","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"LZWWCXRHBPWFLSO2","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"LZWWCXRH","created_at":"2026-07-05T10:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LZWWCXRHBPWFLSO26ABVQPUTQB","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T16:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"dba912f7eda47201d7efb00edbc153d65c8a952391523a9eabe482d0b820a7ef","abstract_canon_sha256":"38b6f73fe8651e02d9ba26676469b738d576cdcd980b6747f25a7e278fec2e8e"},"schema_version":"1.0"},"canonical_sha256":"5e6d615e270bec55c9daf003583e9380655a87aaf0786cb278b2623333006e1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:31.664327Z","signature_b64":"NeG+1Srl4nOAcNQRUICnptkdFsfr3uoYC7Wz/v5/MQLJdhcZptw23LACnb1JwhJ0SrxyH2+1pLcziHFmtUIDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e6d615e270bec55c9daf003583e9380655a87aaf0786cb278b2623333006e1e","last_reissued_at":"2026-07-05T10:05:31.663818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:31.663818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15595","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":"2026-07-05T10:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tB0KVougx11VBWpys1OMQdXoNLfrs0MKyr5Lz6V5UYT5ghbBa3kWTqwpS++9aqtDxHd7f+clg1XXmXDQr7sKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:29:00.566341Z"},"content_sha256":"4b3492f7cda54c333315dad4f40b503697db132ba45ebc540d4bf3608c4fce17","schema_version":"1.0","event_id":"sha256:4b3492f7cda54c333315dad4f40b503697db132ba45ebc540d4bf3608c4fce17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LZWWCXRHBPWFLSO26ABVQPUTQB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SedarEval: Automated Evaluation using Self-Adaptive Rubrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Debing Zhang, Weinong Wang, Xing Wu, Zhiyuan Fan","submitted_at":"2025-01-26T16:45:09Z","abstract_excerpt":"The evaluation paradigm of LLM-as-judge gains popularity due to its significant reduction in human labor and time costs. This approach utilizes one or more large language models (LLMs) to assess the quality of outputs from other LLMs. However, existing methods rely on generic scoring rubrics that fail to consider the specificities of each question and its problem-solving process, compromising precision and stability in assessments. Inspired by human examination scoring processes, we propose a new evaluation paradigm based on self-adaptive rubrics. Specifically, we create detailed scoring rubri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15595","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/2501.15595/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":"2026-07-05T10:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvwiNI8Nag5wTbP3249mkTSICzFvE8a+Vjsv4LUSp9UZ9X1Ga4oXa6bQBHupWRX7Vu7+n6Bvhc3dhYLaloPZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:29:00.566913Z"},"content_sha256":"319171b476a2f321ce73083df9a0a38f4827a64bc716bc0fdb2799e720d92f28","schema_version":"1.0","event_id":"sha256:319171b476a2f321ce73083df9a0a38f4827a64bc716bc0fdb2799e720d92f28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZWWCXRHBPWFLSO26ABVQPUTQB/bundle.json","state_url":"https://pith.science/pith/LZWWCXRHBPWFLSO26ABVQPUTQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZWWCXRHBPWFLSO26ABVQPUTQB/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":"2026-08-11T01:29:00Z","links":{"resolver":"https://pith.science/pith/LZWWCXRHBPWFLSO26ABVQPUTQB","bundle":"https://pith.science/pith/LZWWCXRHBPWFLSO26ABVQPUTQB/bundle.json","state":"https://pith.science/pith/LZWWCXRHBPWFLSO26ABVQPUTQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZWWCXRHBPWFLSO26ABVQPUTQB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LZWWCXRHBPWFLSO26ABVQPUTQB","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":"38b6f73fe8651e02d9ba26676469b738d576cdcd980b6747f25a7e278fec2e8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T16:45:09Z","title_canon_sha256":"dba912f7eda47201d7efb00edbc153d65c8a952391523a9eabe482d0b820a7ef"},"schema_version":"1.0","source":{"id":"2501.15595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15595","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15595v1","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15595","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"LZWWCXRHBPWF","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"LZWWCXRHBPWFLSO2","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"LZWWCXRH","created_at":"2026-07-05T10:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:319171b476a2f321ce73083df9a0a38f4827a64bc716bc0fdb2799e720d92f28","target":"graph","created_at":"2026-07-05T10:05:31Z","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/2501.15595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation paradigm of LLM-as-judge gains popularity due to its significant reduction in human labor and time costs. This approach utilizes one or more large language models (LLMs) to assess the quality of outputs from other LLMs. However, existing methods rely on generic scoring rubrics that fail to consider the specificities of each question and its problem-solving process, compromising precision and stability in assessments. Inspired by human examination scoring processes, we propose a new evaluation paradigm based on self-adaptive rubrics. Specifically, we create detailed scoring rubri","authors_text":"Debing Zhang, Weinong Wang, Xing Wu, Zhiyuan Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T16:45:09Z","title":"SedarEval: Automated Evaluation using Self-Adaptive Rubrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15595","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":"sha256:4b3492f7cda54c333315dad4f40b503697db132ba45ebc540d4bf3608c4fce17","target":"record","created_at":"2026-07-05T10:05:31Z","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":"38b6f73fe8651e02d9ba26676469b738d576cdcd980b6747f25a7e278fec2e8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T16:45:09Z","title_canon_sha256":"dba912f7eda47201d7efb00edbc153d65c8a952391523a9eabe482d0b820a7ef"},"schema_version":"1.0","source":{"id":"2501.15595","kind":"arxiv","version":1}},"canonical_sha256":"5e6d615e270bec55c9daf003583e9380655a87aaf0786cb278b2623333006e1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e6d615e270bec55c9daf003583e9380655a87aaf0786cb278b2623333006e1e","first_computed_at":"2026-07-05T10:05:31.663818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:31.663818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NeG+1Srl4nOAcNQRUICnptkdFsfr3uoYC7Wz/v5/MQLJdhcZptw23LACnb1JwhJ0SrxyH2+1pLcziHFmtUIDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:31.664327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b3492f7cda54c333315dad4f40b503697db132ba45ebc540d4bf3608c4fce17","sha256:319171b476a2f321ce73083df9a0a38f4827a64bc716bc0fdb2799e720d92f28"],"state_sha256":"e87556b6057e3fb6c5861fd90aeabef7d1bc7a5852f2b80b4e40b3a549ac2618"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gta/Pzub9BRA89WahWFIOEO3z+JiOJ0ZpXRvADGBag+cW/qL/ISghsKsnB9QaHsII9YlEBu4DXqn9swCqyjHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:29:00.570713Z","bundle_sha256":"6aa0236678da1159d4011b8760b5e810ecc8a9bffd0f5d02100f9da082ab78bd"}}