{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YOUUB76QMKRV5MROTJPI4UEJC3","short_pith_number":"pith:YOUUB76Q","canonical_record":{"source":{"id":"2410.15466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T18:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7bdf0d33bcec08a8191ee20069608a991fd9cb2e294d93f4ab4998481b411e4","abstract_canon_sha256":"197d43636513a3326804cf561f8d42b449a2198dcb5b505600e58f67ffb56b2f"},"schema_version":"1.0"},"canonical_sha256":"c3a940ffd062a35eb22e9a5e8e508916f6656994db6c283ffbf423acc3db8b88","source":{"kind":"arxiv","id":"2410.15466","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15466","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15466v1","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15466","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"YOUUB76QMKRV","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"YOUUB76QMKRV5MRO","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"YOUUB76Q","created_at":"2026-07-05T09:23:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YOUUB76QMKRV5MROTJPI4UEJC3","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T18:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7bdf0d33bcec08a8191ee20069608a991fd9cb2e294d93f4ab4998481b411e4","abstract_canon_sha256":"197d43636513a3326804cf561f8d42b449a2198dcb5b505600e58f67ffb56b2f"},"schema_version":"1.0"},"canonical_sha256":"c3a940ffd062a35eb22e9a5e8e508916f6656994db6c283ffbf423acc3db8b88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:20.021307Z","signature_b64":"OMUPeMVzKNPV4SQwlTqwJZd0n81bU7EuitBYVuKLGvB6M2LHf9IPp2u1sCn0BAR+sSzclP9HIaa586ryg8/nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3a940ffd062a35eb22e9a5e8e508916f6656994db6c283ffbf423acc3db8b88","last_reissued_at":"2026-07-05T09:23:20.020887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:20.020887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15466","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":"2026-07-05T09:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUwRgQAvnaJuuh0ENuc/bl/bt4IiPSj2CDTBuwDDJCvp4Oj2ZLzFJqJHWoCkwjMUS/7ovUm+FGDitZf2ZBrCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:22:43.161257Z"},"content_sha256":"231bd95aac8a1d406568d54bb14aaa6161dbadbb7ba65d9a427e12cd376fef7c","schema_version":"1.0","event_id":"sha256:231bd95aac8a1d406568d54bb14aaa6161dbadbb7ba65d9a427e12cd376fef7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YOUUB76QMKRV5MROTJPI4UEJC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Keep Guessing? When Considering Inference Scaling, Mind the Baselines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gal Yona, Omer Levy, Or Honovich, Roee Aharoni","submitted_at":"2024-10-20T18:43:05Z","abstract_excerpt":"Scaling inference compute in large language models (LLMs) through repeated sampling consistently increases the coverage (fraction of problems solved) as the number of samples increases. We conjecture that this observed improvement is partially due to the answer distribution of standard evaluation benchmarks, which is skewed towards a relatively small set of common answers. To test this conjecture, we define a baseline that enumerates answers according to their prevalence in the training set. Experiments spanning two domains -- mathematical reasoning and factual knowledge -- reveal that this ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15466","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/2410.15466/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":"2026-07-05T09:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4+KSuP9WdEypb+6eass64MLqm6SKQF18YidNC85AYEraDj8nScGJkviFqTPKufroMh5Xea5wxQf74dmIrJEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:22:43.161998Z"},"content_sha256":"d7c00707a2cc232771bf74630328237abf693f23194861b931bfc590af0482b5","schema_version":"1.0","event_id":"sha256:d7c00707a2cc232771bf74630328237abf693f23194861b931bfc590af0482b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOUUB76QMKRV5MROTJPI4UEJC3/bundle.json","state_url":"https://pith.science/pith/YOUUB76QMKRV5MROTJPI4UEJC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOUUB76QMKRV5MROTJPI4UEJC3/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":"2026-08-12T12:22:43Z","links":{"resolver":"https://pith.science/pith/YOUUB76QMKRV5MROTJPI4UEJC3","bundle":"https://pith.science/pith/YOUUB76QMKRV5MROTJPI4UEJC3/bundle.json","state":"https://pith.science/pith/YOUUB76QMKRV5MROTJPI4UEJC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOUUB76QMKRV5MROTJPI4UEJC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YOUUB76QMKRV5MROTJPI4UEJC3","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":"197d43636513a3326804cf561f8d42b449a2198dcb5b505600e58f67ffb56b2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T18:43:05Z","title_canon_sha256":"d7bdf0d33bcec08a8191ee20069608a991fd9cb2e294d93f4ab4998481b411e4"},"schema_version":"1.0","source":{"id":"2410.15466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15466","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15466v1","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15466","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"YOUUB76QMKRV","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"YOUUB76QMKRV5MRO","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"YOUUB76Q","created_at":"2026-07-05T09:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:d7c00707a2cc232771bf74630328237abf693f23194861b931bfc590af0482b5","target":"graph","created_at":"2026-07-05T09:23:20Z","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/2410.15466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling inference compute in large language models (LLMs) through repeated sampling consistently increases the coverage (fraction of problems solved) as the number of samples increases. We conjecture that this observed improvement is partially due to the answer distribution of standard evaluation benchmarks, which is skewed towards a relatively small set of common answers. To test this conjecture, we define a baseline that enumerates answers according to their prevalence in the training set. Experiments spanning two domains -- mathematical reasoning and factual knowledge -- reveal that this ba","authors_text":"Gal Yona, Omer Levy, Or Honovich, Roee Aharoni","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T18:43:05Z","title":"Keep Guessing? When Considering Inference Scaling, Mind the Baselines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15466","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":"sha256:231bd95aac8a1d406568d54bb14aaa6161dbadbb7ba65d9a427e12cd376fef7c","target":"record","created_at":"2026-07-05T09:23:20Z","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":"197d43636513a3326804cf561f8d42b449a2198dcb5b505600e58f67ffb56b2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T18:43:05Z","title_canon_sha256":"d7bdf0d33bcec08a8191ee20069608a991fd9cb2e294d93f4ab4998481b411e4"},"schema_version":"1.0","source":{"id":"2410.15466","kind":"arxiv","version":1}},"canonical_sha256":"c3a940ffd062a35eb22e9a5e8e508916f6656994db6c283ffbf423acc3db8b88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a940ffd062a35eb22e9a5e8e508916f6656994db6c283ffbf423acc3db8b88","first_computed_at":"2026-07-05T09:23:20.020887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:20.020887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OMUPeMVzKNPV4SQwlTqwJZd0n81bU7EuitBYVuKLGvB6M2LHf9IPp2u1sCn0BAR+sSzclP9HIaa586ryg8/nCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:20.021307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:231bd95aac8a1d406568d54bb14aaa6161dbadbb7ba65d9a427e12cd376fef7c","sha256:d7c00707a2cc232771bf74630328237abf693f23194861b931bfc590af0482b5"],"state_sha256":"b2bb45452aa78d1bca3cd0a9b4e8df3375b5abfa2898c3578864d55cc00f642b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qOSxWKr+g8IpL203CWfotETfLkQTHvBMNuO4899zXtdfcya0lsJxrSpSpqi1x4V2or2RfHmu6SvZiiEsKsgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:22:43.168068Z","bundle_sha256":"21ca359cbcd5b228ce766ac20557d7e369b7956c2322a54f63a9c49a9daa2c2e"}}