{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XCALAXG6M7E2TP4GJJNN6BYSWS","short_pith_number":"pith:XCALAXG6","canonical_record":{"source":{"id":"2407.10817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:33:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"054d86dd07eab7a0d7069b06c8aa44fd0cd7f304021a382831903052c1c4ec98","abstract_canon_sha256":"25736d1a5d2bdc952d39a840276f87f3b9d97f3cbb4a6c6df66bf6e2b1f3df69"},"schema_version":"1.0"},"canonical_sha256":"b880b05cde67c9a9bf864a5adf0712b4ac2beb3168bdb6dd0185b4bc9c367804","source":{"kind":"arxiv","id":"2407.10817","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10817","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10817v1","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10817","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"XCALAXG6M7E2","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"XCALAXG6M7E2TP4G","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"XCALAXG6","created_at":"2026-07-05T08:44:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XCALAXG6M7E2TP4GJJNN6BYSWS","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:33:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"054d86dd07eab7a0d7069b06c8aa44fd0cd7f304021a382831903052c1c4ec98","abstract_canon_sha256":"25736d1a5d2bdc952d39a840276f87f3b9d97f3cbb4a6c6df66bf6e2b1f3df69"},"schema_version":"1.0"},"canonical_sha256":"b880b05cde67c9a9bf864a5adf0712b4ac2beb3168bdb6dd0185b4bc9c367804","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:04.606838Z","signature_b64":"TP5FmsmVwytLkTzjyLMm5b2r805tWb0Lr8ALig/v1mD8obf+LIcNfA1AVC0rVHi0gW5iu7oQdFvk1EFGmz7bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b880b05cde67c9a9bf864a5adf0712b4ac2beb3168bdb6dd0185b4bc9c367804","last_reissued_at":"2026-07-05T08:44:04.606324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:04.606324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10817","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":"2026-07-05T08:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+YVEDkU7xMqRXtGuF+J2WDHyXbTbajjOO72D60e9rlpYOMuuTOtcmNyZzsqImA2B2OafAZrHZmENtOta1fTRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:09:46.316674Z"},"content_sha256":"5a1bd5933861e6f57baeeaa80dfcb65bf1564ba310a735e9f68ac365f9812777","schema_version":"1.0","event_id":"sha256:5a1bd5933861e6f57baeeaa80dfcb65bf1564ba310a735e9f68ac365f9812777"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XCALAXG6M7E2TP4GJJNN6BYSWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chris Tar, Kalpesh Krishna, Manaal Faruqui, Salaheddin Alzubi, Tu Vu, Yun-hsuan Sung","submitted_at":"2024-07-15T15:33:45Z","abstract_excerpt":"As large language models (LLMs) advance, it becomes more challenging to reliably evaluate their output due to the high costs of human evaluation. To make progress towards better LLM autoraters, we introduce FLAMe, a family of Foundational Large Autorater Models. FLAMe is trained on our large and diverse collection of 100+ quality assessment tasks comprising 5M+ human judgments, curated and standardized using publicly released human evaluations from previous research. FLAMe significantly improves generalization to a wide variety of held-out tasks, outperforming LLMs trained on proprietary data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10817","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/2407.10817/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":"2026-07-05T08:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VuFspJllnKI5/5txAbuz59DOa22CkoI6Bq2WDqjMKZUfW6yVnWHIBPMxnlV1QwQMGhSSdUQXMD23N+rtezPwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:09:46.319206Z"},"content_sha256":"f0b02ba3e5d9dbe7d5b8ab80421d15d137ae07df817d32e8909b4831213a2a68","schema_version":"1.0","event_id":"sha256:f0b02ba3e5d9dbe7d5b8ab80421d15d137ae07df817d32e8909b4831213a2a68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCALAXG6M7E2TP4GJJNN6BYSWS/bundle.json","state_url":"https://pith.science/pith/XCALAXG6M7E2TP4GJJNN6BYSWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCALAXG6M7E2TP4GJJNN6BYSWS/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":"2026-08-06T02:09:46Z","links":{"resolver":"https://pith.science/pith/XCALAXG6M7E2TP4GJJNN6BYSWS","bundle":"https://pith.science/pith/XCALAXG6M7E2TP4GJJNN6BYSWS/bundle.json","state":"https://pith.science/pith/XCALAXG6M7E2TP4GJJNN6BYSWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCALAXG6M7E2TP4GJJNN6BYSWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XCALAXG6M7E2TP4GJJNN6BYSWS","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":"25736d1a5d2bdc952d39a840276f87f3b9d97f3cbb4a6c6df66bf6e2b1f3df69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:33:45Z","title_canon_sha256":"054d86dd07eab7a0d7069b06c8aa44fd0cd7f304021a382831903052c1c4ec98"},"schema_version":"1.0","source":{"id":"2407.10817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10817","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10817v1","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10817","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"XCALAXG6M7E2","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"XCALAXG6M7E2TP4G","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"XCALAXG6","created_at":"2026-07-05T08:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:f0b02ba3e5d9dbe7d5b8ab80421d15d137ae07df817d32e8909b4831213a2a68","target":"graph","created_at":"2026-07-05T08:44:04Z","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/2407.10817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) advance, it becomes more challenging to reliably evaluate their output due to the high costs of human evaluation. To make progress towards better LLM autoraters, we introduce FLAMe, a family of Foundational Large Autorater Models. FLAMe is trained on our large and diverse collection of 100+ quality assessment tasks comprising 5M+ human judgments, curated and standardized using publicly released human evaluations from previous research. FLAMe significantly improves generalization to a wide variety of held-out tasks, outperforming LLMs trained on proprietary data ","authors_text":"Chris Tar, Kalpesh Krishna, Manaal Faruqui, Salaheddin Alzubi, Tu Vu, Yun-hsuan Sung","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:33:45Z","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10817","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":"sha256:5a1bd5933861e6f57baeeaa80dfcb65bf1564ba310a735e9f68ac365f9812777","target":"record","created_at":"2026-07-05T08:44:04Z","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":"25736d1a5d2bdc952d39a840276f87f3b9d97f3cbb4a6c6df66bf6e2b1f3df69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:33:45Z","title_canon_sha256":"054d86dd07eab7a0d7069b06c8aa44fd0cd7f304021a382831903052c1c4ec98"},"schema_version":"1.0","source":{"id":"2407.10817","kind":"arxiv","version":1}},"canonical_sha256":"b880b05cde67c9a9bf864a5adf0712b4ac2beb3168bdb6dd0185b4bc9c367804","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b880b05cde67c9a9bf864a5adf0712b4ac2beb3168bdb6dd0185b4bc9c367804","first_computed_at":"2026-07-05T08:44:04.606324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:04.606324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TP5FmsmVwytLkTzjyLMm5b2r805tWb0Lr8ALig/v1mD8obf+LIcNfA1AVC0rVHi0gW5iu7oQdFvk1EFGmz7bCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:04.606838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a1bd5933861e6f57baeeaa80dfcb65bf1564ba310a735e9f68ac365f9812777","sha256:f0b02ba3e5d9dbe7d5b8ab80421d15d137ae07df817d32e8909b4831213a2a68"],"state_sha256":"a43f8e0653143adb2f9395c02ec7fb8dcfc26799b32120f8bc27561d3873608b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EzL+tZUQZFyqe1JzumWTSCczfr/sIk0XzgnLh2sZUjp+M1zOOaQekpuqSSwLBGWekc7sTZwFbHeJJTGFm2r7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:09:46.818638Z","bundle_sha256":"64ce25ff3ae32e01ca43cdbe12f4cac30a1bbf8f760c8dbe2edbd6e65b4de78b"}}