{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AHH6KSIISMDVQH5CYZXX7VLJS3","short_pith_number":"pith:AHH6KSII","canonical_record":{"source":{"id":"2311.02807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T00:21:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3f5f80505fa09639c22d3f68cc07baa69b75716c8367d30facfae5ce05d2ad1d","abstract_canon_sha256":"ccf5e75994cd71d4a3f41ea5e143f255c20fbaa94c55c3cf0fa2e9cb633d5ec5"},"schema_version":"1.0"},"canonical_sha256":"01cfe549089307581fa2c66f7fd56996cb772a0282f8ba87fb4463fdfb8cacd2","source":{"kind":"arxiv","id":"2311.02807","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02807","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02807v2","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02807","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"AHH6KSIISMDV","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"AHH6KSIISMDVQH5C","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"AHH6KSII","created_at":"2026-07-05T08:15:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AHH6KSIISMDVQH5CYZXX7VLJS3","target":"record","payload":{"canonical_record":{"source":{"id":"2311.02807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T00:21:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3f5f80505fa09639c22d3f68cc07baa69b75716c8367d30facfae5ce05d2ad1d","abstract_canon_sha256":"ccf5e75994cd71d4a3f41ea5e143f255c20fbaa94c55c3cf0fa2e9cb633d5ec5"},"schema_version":"1.0"},"canonical_sha256":"01cfe549089307581fa2c66f7fd56996cb772a0282f8ba87fb4463fdfb8cacd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:41.458047Z","signature_b64":"d9I2AwfZmiDimoEAlSl/5v0KvmhYpm9Vr5pm2RNcogak6eupPUZCkGSQnFx7u7kJmUYv/8sacZiGrYYeivtvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01cfe549089307581fa2c66f7fd56996cb772a0282f8ba87fb4463fdfb8cacd2","last_reissued_at":"2026-07-05T08:15:41.457570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:41.457570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.02807","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":"2026-07-05T08:15:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQjvRuRCf+q3NW0dfGJ4JKrwH/QqaY1YygfuDcoOlTpxdiqR/bmqeL3sSfDx4UocTX617O2h/ECNSELmDA+jBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:26:21.666356Z"},"content_sha256":"f5b22f96d64b569ac704aec37964a0256fb740f0051963a41a181d0597a84685","schema_version":"1.0","event_id":"sha256:f5b22f96d64b569ac704aec37964a0256fb740f0051963a41a181d0597a84685"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AHH6KSIISMDVQH5CYZXX7VLJS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QualEval: Qualitative Evaluation for Model Improvement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ameet Deshpande, Ashish Sabharwal, Ashwin Kalyan, Karthik Narasimhan, Peter Clark, Tanmay Rajpurohit, Vishvak Murahari","submitted_at":"2023-11-06T00:21:44Z","abstract_excerpt":"Quantitative evaluation metrics have traditionally been pivotal in gauging the advancements of artificial intelligence systems, including large language models (LLMs). However, these metrics have inherent limitations. Given the intricate nature of real-world tasks, a single scalar to quantify and compare is insufficient to capture the fine-grained nuances of model behavior. Metrics serve only as a way to compare and benchmark models, and do not yield actionable diagnostics, thus making the model improvement process challenging. Model developers find themselves amid extensive manual efforts inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02807","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/2311.02807/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":"2026-07-05T08:15:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IymSN445HD0SsgYG20fm7zyAEEOaig0OcLUBulH3SuYVmvRf1tPeiAJUx/lFgCbiz92fZZcFGu4Poe9bZLcyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:26:21.667313Z"},"content_sha256":"d61f540e22f64f005901d3e00b7bffefc5725f70bb4f399569549ebc246d2227","schema_version":"1.0","event_id":"sha256:d61f540e22f64f005901d3e00b7bffefc5725f70bb4f399569549ebc246d2227"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHH6KSIISMDVQH5CYZXX7VLJS3/bundle.json","state_url":"https://pith.science/pith/AHH6KSIISMDVQH5CYZXX7VLJS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHH6KSIISMDVQH5CYZXX7VLJS3/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":"2026-08-03T17:26:21Z","links":{"resolver":"https://pith.science/pith/AHH6KSIISMDVQH5CYZXX7VLJS3","bundle":"https://pith.science/pith/AHH6KSIISMDVQH5CYZXX7VLJS3/bundle.json","state":"https://pith.science/pith/AHH6KSIISMDVQH5CYZXX7VLJS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHH6KSIISMDVQH5CYZXX7VLJS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AHH6KSIISMDVQH5CYZXX7VLJS3","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":"ccf5e75994cd71d4a3f41ea5e143f255c20fbaa94c55c3cf0fa2e9cb633d5ec5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T00:21:44Z","title_canon_sha256":"3f5f80505fa09639c22d3f68cc07baa69b75716c8367d30facfae5ce05d2ad1d"},"schema_version":"1.0","source":{"id":"2311.02807","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02807","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02807v2","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02807","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"AHH6KSIISMDV","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"AHH6KSIISMDVQH5C","created_at":"2026-07-05T08:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"AHH6KSII","created_at":"2026-07-05T08:15:41Z"}],"graph_snapshots":[{"event_id":"sha256:d61f540e22f64f005901d3e00b7bffefc5725f70bb4f399569549ebc246d2227","target":"graph","created_at":"2026-07-05T08:15:41Z","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/2311.02807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantitative evaluation metrics have traditionally been pivotal in gauging the advancements of artificial intelligence systems, including large language models (LLMs). However, these metrics have inherent limitations. Given the intricate nature of real-world tasks, a single scalar to quantify and compare is insufficient to capture the fine-grained nuances of model behavior. Metrics serve only as a way to compare and benchmark models, and do not yield actionable diagnostics, thus making the model improvement process challenging. Model developers find themselves amid extensive manual efforts inv","authors_text":"Ameet Deshpande, Ashish Sabharwal, Ashwin Kalyan, Karthik Narasimhan, Peter Clark, Tanmay Rajpurohit, Vishvak Murahari","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T00:21:44Z","title":"QualEval: Qualitative Evaluation for Model Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02807","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:f5b22f96d64b569ac704aec37964a0256fb740f0051963a41a181d0597a84685","target":"record","created_at":"2026-07-05T08:15:41Z","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":"ccf5e75994cd71d4a3f41ea5e143f255c20fbaa94c55c3cf0fa2e9cb633d5ec5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T00:21:44Z","title_canon_sha256":"3f5f80505fa09639c22d3f68cc07baa69b75716c8367d30facfae5ce05d2ad1d"},"schema_version":"1.0","source":{"id":"2311.02807","kind":"arxiv","version":2}},"canonical_sha256":"01cfe549089307581fa2c66f7fd56996cb772a0282f8ba87fb4463fdfb8cacd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01cfe549089307581fa2c66f7fd56996cb772a0282f8ba87fb4463fdfb8cacd2","first_computed_at":"2026-07-05T08:15:41.457570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:41.457570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d9I2AwfZmiDimoEAlSl/5v0KvmhYpm9Vr5pm2RNcogak6eupPUZCkGSQnFx7u7kJmUYv/8sacZiGrYYeivtvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:41.458047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02807","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5b22f96d64b569ac704aec37964a0256fb740f0051963a41a181d0597a84685","sha256:d61f540e22f64f005901d3e00b7bffefc5725f70bb4f399569549ebc246d2227"],"state_sha256":"0e3b07bb06a883c039b22e38cd8d87cf644a96c1e8630851bbc1bd889bd06f62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1tZci023s7JrgCPVNuZNsi+jO6WyBWaM8LTrQaNI9GoyISzFvCD1sd8WGWwT3lKYjoplwYJlBCrHUNR+OpaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:26:21.675034Z","bundle_sha256":"28325e54d68bfd24412fbc38582bc7e84de20cd5a556c3538dc7fd5582e46627"}}