{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IIAPMSPHIVNUH2UKNWZATTC2ZZ","short_pith_number":"pith:IIAPMSPH","canonical_record":{"source":{"id":"2606.08679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-07T15:31:29Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ME"],"title_canon_sha256":"9f1294bec21f83fc07e4bde3e3a3fd6ca0cc77f278986039ecb480909e9c7905","abstract_canon_sha256":"fd9af829c441003d77c5144c0537a434fb913655daa7c30454471c6b5d9c0ab0"},"schema_version":"1.0"},"canonical_sha256":"4200f649e7455b43ea8a6db209cc5ace423a2bd8c19d1202ca90cc9a51ae5c0e","source":{"kind":"arxiv","id":"2606.08679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08679","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08679v1","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08679","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"IIAPMSPHIVNU","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"IIAPMSPHIVNUH2UK","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"IIAPMSPH","created_at":"2026-06-09T01:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IIAPMSPHIVNUH2UKNWZATTC2ZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-07T15:31:29Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ME"],"title_canon_sha256":"9f1294bec21f83fc07e4bde3e3a3fd6ca0cc77f278986039ecb480909e9c7905","abstract_canon_sha256":"fd9af829c441003d77c5144c0537a434fb913655daa7c30454471c6b5d9c0ab0"},"schema_version":"1.0"},"canonical_sha256":"4200f649e7455b43ea8a6db209cc5ace423a2bd8c19d1202ca90cc9a51ae5c0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:47.256307Z","signature_b64":"nDtG9aDcw7iKJxPsZvKvPDfWD4S8BjNlS961rc3O9gkpqKYKlLqex0Po03gwf4i/dyokh6Xb9hX/P9Ign9xnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4200f649e7455b43ea8a6db209cc5ace423a2bd8c19d1202ca90cc9a51ae5c0e","last_reissued_at":"2026-06-09T01:05:47.255887Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:47.255887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08679","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":"2026-06-09T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKHFW0py6I2OQ9DfAOYg8bGSram7+VTSvevcRK3rGVzN+gRY1y9aQE1zJZOIZRotqTeXhVA/XKLC4Kb20brCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T09:15:59.389508Z"},"content_sha256":"97bc783188250615c22f77f9155b82fb9c283bca425a0d38ee816a5f12a88e87","schema_version":"1.0","event_id":"sha256:97bc783188250615c22f77f9155b82fb9c283bca425a0d38ee816a5f12a88e87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IIAPMSPHIVNUH2UKNWZATTC2ZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Bitya Neuhof, Yuval Benjamini","submitted_at":"2026-06-07T15:31:29Z","abstract_excerpt":"Pretrained models are often evaluated on multi-task leaderboards to measure their applicability in diverse contexts. However, current methods for aggregating performance across tasks into leaderboard-level rankings do not address the uncertainty and variability at the task level. While recent works have proposed interval-based model rankings, the principled aggregation of uncertainty from individual tasks to leaderboard-level rankings remains unaddressed, and variation in models' performance across tasks is frequently obscured. In this work, we introduce a hierarchical framework that construct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08679","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/2606.08679/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":"2026-06-09T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rSQNblibWyUzC4IAZVOE23b3YE8akfNXdXKIVvfBQO0vaRWynl0mJwYBQQ0zUag6XSfNyW4ZK+slI5hE6AFMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T09:15:59.389888Z"},"content_sha256":"a4e73912bad0c8316b7ec116934d7d2de08f2b30677d905bef27779621a9bb42","schema_version":"1.0","event_id":"sha256:a4e73912bad0c8316b7ec116934d7d2de08f2b30677d905bef27779621a9bb42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ/bundle.json","state_url":"https://pith.science/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ/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":"2026-06-21T09:15:59Z","links":{"resolver":"https://pith.science/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ","bundle":"https://pith.science/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ/bundle.json","state":"https://pith.science/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIAPMSPHIVNUH2UKNWZATTC2ZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IIAPMSPHIVNUH2UKNWZATTC2ZZ","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":"fd9af829c441003d77c5144c0537a434fb913655daa7c30454471c6b5d9c0ab0","cross_cats_sorted":["cs.CL","cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-07T15:31:29Z","title_canon_sha256":"9f1294bec21f83fc07e4bde3e3a3fd6ca0cc77f278986039ecb480909e9c7905"},"schema_version":"1.0","source":{"id":"2606.08679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08679","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08679v1","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08679","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"IIAPMSPHIVNU","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"IIAPMSPHIVNUH2UK","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"IIAPMSPH","created_at":"2026-06-09T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:a4e73912bad0c8316b7ec116934d7d2de08f2b30677d905bef27779621a9bb42","target":"graph","created_at":"2026-06-09T01:05:47Z","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/2606.08679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained models are often evaluated on multi-task leaderboards to measure their applicability in diverse contexts. However, current methods for aggregating performance across tasks into leaderboard-level rankings do not address the uncertainty and variability at the task level. While recent works have proposed interval-based model rankings, the principled aggregation of uncertainty from individual tasks to leaderboard-level rankings remains unaddressed, and variation in models' performance across tasks is frequently obscured. In this work, we introduce a hierarchical framework that construct","authors_text":"Bitya Neuhof, Yuval Benjamini","cross_cats":["cs.CL","cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-07T15:31:29Z","title":"Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08679","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":"sha256:97bc783188250615c22f77f9155b82fb9c283bca425a0d38ee816a5f12a88e87","target":"record","created_at":"2026-06-09T01:05:47Z","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":"fd9af829c441003d77c5144c0537a434fb913655daa7c30454471c6b5d9c0ab0","cross_cats_sorted":["cs.CL","cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-07T15:31:29Z","title_canon_sha256":"9f1294bec21f83fc07e4bde3e3a3fd6ca0cc77f278986039ecb480909e9c7905"},"schema_version":"1.0","source":{"id":"2606.08679","kind":"arxiv","version":1}},"canonical_sha256":"4200f649e7455b43ea8a6db209cc5ace423a2bd8c19d1202ca90cc9a51ae5c0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4200f649e7455b43ea8a6db209cc5ace423a2bd8c19d1202ca90cc9a51ae5c0e","first_computed_at":"2026-06-09T01:05:47.255887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:47.255887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDtG9aDcw7iKJxPsZvKvPDfWD4S8BjNlS961rc3O9gkpqKYKlLqex0Po03gwf4i/dyokh6Xb9hX/P9Ign9xnBg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:47.256307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97bc783188250615c22f77f9155b82fb9c283bca425a0d38ee816a5f12a88e87","sha256:a4e73912bad0c8316b7ec116934d7d2de08f2b30677d905bef27779621a9bb42"],"state_sha256":"8ce724f2e6c02c5f48981b08d3e42befd0bba5336f626f787481f0aa181793b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9cdxwoQB5jnDTynqbh+xHZvN20uBBvzu0ABFbw1rZ0jRnSyHWBZ7Lo3I+ytoXQjR1c8Ph8HPP9bOmEVIjxWwDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-21T09:15:59.391951Z","bundle_sha256":"487b7aef07c6f06ca978913c5b25a24db2ba64771605c391dcc57e7821c529c1"}}