{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KTSKSQYBBNEVPY22V3G52OUE62","short_pith_number":"pith:KTSKSQYB","canonical_record":{"source":{"id":"2410.02381","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T11:01:25Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"09f9cf213df7114ab922310add6a8024aa18c61eb364176914a0277035d5b94b","abstract_canon_sha256":"91e6ac733105f35641376ed4a6f8c2e47c15e2c12136b3e8491e4d918f1b516e"},"schema_version":"1.0"},"canonical_sha256":"54e4a943010b4957e35aaecddd3a84f684ac3e90693b007a9e1e15dfbc6ea123","source":{"kind":"arxiv","id":"2410.02381","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02381","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02381v4","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02381","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"KTSKSQYBBNEV","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"KTSKSQYBBNEVPY22","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"KTSKSQYB","created_at":"2026-07-05T10:22:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KTSKSQYBBNEVPY22V3G52OUE62","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02381","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T11:01:25Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"09f9cf213df7114ab922310add6a8024aa18c61eb364176914a0277035d5b94b","abstract_canon_sha256":"91e6ac733105f35641376ed4a6f8c2e47c15e2c12136b3e8491e4d918f1b516e"},"schema_version":"1.0"},"canonical_sha256":"54e4a943010b4957e35aaecddd3a84f684ac3e90693b007a9e1e15dfbc6ea123","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:05.557906Z","signature_b64":"bhKyVIMVfw5iL+vAkI4UTwvckmWaSgD+hO1vkWPOT0rLRQiqERmdq6yV3lL2ULzGapWfwXmsHhNtR1imXbO1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54e4a943010b4957e35aaecddd3a84f684ac3e90693b007a9e1e15dfbc6ea123","last_reissued_at":"2026-07-05T10:22:05.557411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:05.557411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02381","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"016ZXFozUPFuZjwo14bcU2OdF2t3sGs1VumzMxkLb45e3aQMZ1JxqCTwmuoV0+xNcaxS70EXWFvud0l20JKHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:01:47.505923Z"},"content_sha256":"c60f9d917c72e1ed6ac558194b2ff0a63496b7db52b51efa7d13ac6f433a4cd5","schema_version":"1.0","event_id":"sha256:c60f9d917c72e1ed6ac558194b2ff0a63496b7db52b51efa7d13ac6f433a4cd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KTSKSQYBBNEVPY22V3G52OUE62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Anugraha, Derry Tanti Wijaya, Garry Kuwanto, Genta Indra Winata, Lucky Susanto","submitted_at":"2024-10-03T11:01:25Z","abstract_excerpt":"Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as metrics often excel in one particular area but not across all dimensions. To address this, it is essential to systematically calibrate metrics to specific aspects of human preference, catering to the unique characteristics of each aspect. We introduce MetaMetrics, a calibrated meta-metric designed to evaluate generation tasks across different modalities in a su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02381","kind":"arxiv","version":4},"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/2410.02381/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":"2026-07-05T10:22:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zm/QAO9rXANfP35ITo27DnlaCrPjYQaPqs79QIxl+N1ueS1p8bbLgf3p2iKL1cHxibmO2MnmIKvqzKdoXO6TCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:01:47.506481Z"},"content_sha256":"dc47ed86cafd7779a4e3580d0a53bd8b1db332ecc76bab9db839e540d744b1c6","schema_version":"1.0","event_id":"sha256:dc47ed86cafd7779a4e3580d0a53bd8b1db332ecc76bab9db839e540d744b1c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTSKSQYBBNEVPY22V3G52OUE62/bundle.json","state_url":"https://pith.science/pith/KTSKSQYBBNEVPY22V3G52OUE62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTSKSQYBBNEVPY22V3G52OUE62/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":"2026-08-08T21:01:47Z","links":{"resolver":"https://pith.science/pith/KTSKSQYBBNEVPY22V3G52OUE62","bundle":"https://pith.science/pith/KTSKSQYBBNEVPY22V3G52OUE62/bundle.json","state":"https://pith.science/pith/KTSKSQYBBNEVPY22V3G52OUE62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTSKSQYBBNEVPY22V3G52OUE62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KTSKSQYBBNEVPY22V3G52OUE62","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":"91e6ac733105f35641376ed4a6f8c2e47c15e2c12136b3e8491e4d918f1b516e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T11:01:25Z","title_canon_sha256":"09f9cf213df7114ab922310add6a8024aa18c61eb364176914a0277035d5b94b"},"schema_version":"1.0","source":{"id":"2410.02381","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02381","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02381v4","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02381","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"KTSKSQYBBNEV","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"KTSKSQYBBNEVPY22","created_at":"2026-07-05T10:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"KTSKSQYB","created_at":"2026-07-05T10:22:05Z"}],"graph_snapshots":[{"event_id":"sha256:dc47ed86cafd7779a4e3580d0a53bd8b1db332ecc76bab9db839e540d744b1c6","target":"graph","created_at":"2026-07-05T10:22:05Z","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/2410.02381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as metrics often excel in one particular area but not across all dimensions. To address this, it is essential to systematically calibrate metrics to specific aspects of human preference, catering to the unique characteristics of each aspect. We introduce MetaMetrics, a calibrated meta-metric designed to evaluate generation tasks across different modalities in a su","authors_text":"David Anugraha, Derry Tanti Wijaya, Garry Kuwanto, Genta Indra Winata, Lucky Susanto","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T11:01:25Z","title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02381","kind":"arxiv","version":4},"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:c60f9d917c72e1ed6ac558194b2ff0a63496b7db52b51efa7d13ac6f433a4cd5","target":"record","created_at":"2026-07-05T10:22:05Z","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":"91e6ac733105f35641376ed4a6f8c2e47c15e2c12136b3e8491e4d918f1b516e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T11:01:25Z","title_canon_sha256":"09f9cf213df7114ab922310add6a8024aa18c61eb364176914a0277035d5b94b"},"schema_version":"1.0","source":{"id":"2410.02381","kind":"arxiv","version":4}},"canonical_sha256":"54e4a943010b4957e35aaecddd3a84f684ac3e90693b007a9e1e15dfbc6ea123","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54e4a943010b4957e35aaecddd3a84f684ac3e90693b007a9e1e15dfbc6ea123","first_computed_at":"2026-07-05T10:22:05.557411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:05.557411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bhKyVIMVfw5iL+vAkI4UTwvckmWaSgD+hO1vkWPOT0rLRQiqERmdq6yV3lL2ULzGapWfwXmsHhNtR1imXbO1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:05.557906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02381","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c60f9d917c72e1ed6ac558194b2ff0a63496b7db52b51efa7d13ac6f433a4cd5","sha256:dc47ed86cafd7779a4e3580d0a53bd8b1db332ecc76bab9db839e540d744b1c6"],"state_sha256":"20398d11f5851bed3aa955fa51571b7220cf6f76113a4eb53a1f5afa62778640"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1KDg3x5tgRVSnMg2Qf6tPAJ3vmiaHBrh88rk6UhaVbF79TATNgivWAk0M3+9SZI4kzkFnDL5OVWvTRad6MUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:01:47.510018Z","bundle_sha256":"d862d3f0b5248b4ef5bb34069a6de0612229f6c4169bbe53e5a61651a23f2902"}}