{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MYPJ2XRD4KO4IHKTCCTSNJLTCV","short_pith_number":"pith:MYPJ2XRD","canonical_record":{"source":{"id":"2506.00723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T21:49:17Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"86a65399116464c9bfc9be5edc183c391765db44113163997b9c57ee42b7647c","abstract_canon_sha256":"5a32d8c0c7fe159bf92f1b53d7ce54a5636b37ee112cc45d04d6dec78aba5376"},"schema_version":"1.0"},"canonical_sha256":"661e9d5e23e29dc41d5310a726a573155e2dd740d72c2df6aafd78b70c84f536","source":{"kind":"arxiv","id":"2506.00723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00723","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00723v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00723","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"MYPJ2XRD4KO4","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"MYPJ2XRD4KO4IHKT","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"MYPJ2XRD","created_at":"2026-07-05T11:13:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MYPJ2XRD4KO4IHKTCCTSNJLTCV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T21:49:17Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"86a65399116464c9bfc9be5edc183c391765db44113163997b9c57ee42b7647c","abstract_canon_sha256":"5a32d8c0c7fe159bf92f1b53d7ce54a5636b37ee112cc45d04d6dec78aba5376"},"schema_version":"1.0"},"canonical_sha256":"661e9d5e23e29dc41d5310a726a573155e2dd740d72c2df6aafd78b70c84f536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:39.333356Z","signature_b64":"+GP35eo3tHLQ6+wY3A+Vhna4TR6ofPzhj/i03L8U6Em940vYts0JSjD7iM7yOZUF5O7dfxNNvXZu5gZAYjwiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"661e9d5e23e29dc41d5310a726a573155e2dd740d72c2df6aafd78b70c84f536","last_reissued_at":"2026-07-05T11:13:39.332781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:39.332781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00723","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":"2026-07-05T11:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCGT/uT8wtGvsa0GdyGJ2h7t/Gsu+Xqeuk5lgI6zJ8BvCKfrdoAEi2RtfJVJhdCbhfVfZKajevttl5mefdb4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:09.915837Z"},"content_sha256":"f393c48f1397de35931360e2027a01d61cb69e10fdb097fe25e5e492e18256ba","schema_version":"1.0","event_id":"sha256:f393c48f1397de35931360e2027a01d61cb69e10fdb097fe25e5e492e18256ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MYPJ2XRD4KO4IHKTCCTSNJLTCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pitfalls in Evaluating Language Model Forecasters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Daniel Paleka, Florian Tram\\`er, Jonas Geiping, Shashwat Goel","submitted_at":"2025-05-31T21:49:17Z","abstract_excerpt":"Large language models (LLMs) have recently been applied to forecasting tasks, with some works claiming these systems match or exceed human performance. In this paper, we argue that, as a community, we should be careful about such conclusions as evaluating LLM forecasters presents unique challenges. We identify two broad categories of issues: (1) difficulty in trusting evaluation results due to many forms of temporal leakage, and (2) difficulty in extrapolating from evaluation performance to real-world forecasting. Through systematic analysis and concrete examples from prior work, we demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00723","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/2506.00723/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":"2026-07-05T11:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y48MhRalP+yQJjSM5cfjQN395h+LagOu/MFuxineMvCdEsksMA5x++/y5VoMXJKsmbktz/fkglBtD3j/i2u0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:09.916404Z"},"content_sha256":"52cb7e669facdb5884866f252dd452332d70aa5f9d9c415fece397e09c46a32f","schema_version":"1.0","event_id":"sha256:52cb7e669facdb5884866f252dd452332d70aa5f9d9c415fece397e09c46a32f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV/bundle.json","state_url":"https://pith.science/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV/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":"2026-08-08T16:20:09Z","links":{"resolver":"https://pith.science/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV","bundle":"https://pith.science/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV/bundle.json","state":"https://pith.science/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYPJ2XRD4KO4IHKTCCTSNJLTCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MYPJ2XRD4KO4IHKTCCTSNJLTCV","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":"5a32d8c0c7fe159bf92f1b53d7ce54a5636b37ee112cc45d04d6dec78aba5376","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T21:49:17Z","title_canon_sha256":"86a65399116464c9bfc9be5edc183c391765db44113163997b9c57ee42b7647c"},"schema_version":"1.0","source":{"id":"2506.00723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00723","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00723v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00723","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"MYPJ2XRD4KO4","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"MYPJ2XRD4KO4IHKT","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"MYPJ2XRD","created_at":"2026-07-05T11:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:52cb7e669facdb5884866f252dd452332d70aa5f9d9c415fece397e09c46a32f","target":"graph","created_at":"2026-07-05T11:13:39Z","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/2506.00723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently been applied to forecasting tasks, with some works claiming these systems match or exceed human performance. In this paper, we argue that, as a community, we should be careful about such conclusions as evaluating LLM forecasters presents unique challenges. We identify two broad categories of issues: (1) difficulty in trusting evaluation results due to many forms of temporal leakage, and (2) difficulty in extrapolating from evaluation performance to real-world forecasting. Through systematic analysis and concrete examples from prior work, we demonstrat","authors_text":"Daniel Paleka, Florian Tram\\`er, Jonas Geiping, Shashwat Goel","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T21:49:17Z","title":"Pitfalls in Evaluating Language Model Forecasters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00723","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:f393c48f1397de35931360e2027a01d61cb69e10fdb097fe25e5e492e18256ba","target":"record","created_at":"2026-07-05T11:13:39Z","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":"5a32d8c0c7fe159bf92f1b53d7ce54a5636b37ee112cc45d04d6dec78aba5376","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T21:49:17Z","title_canon_sha256":"86a65399116464c9bfc9be5edc183c391765db44113163997b9c57ee42b7647c"},"schema_version":"1.0","source":{"id":"2506.00723","kind":"arxiv","version":1}},"canonical_sha256":"661e9d5e23e29dc41d5310a726a573155e2dd740d72c2df6aafd78b70c84f536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"661e9d5e23e29dc41d5310a726a573155e2dd740d72c2df6aafd78b70c84f536","first_computed_at":"2026-07-05T11:13:39.332781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:39.332781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+GP35eo3tHLQ6+wY3A+Vhna4TR6ofPzhj/i03L8U6Em940vYts0JSjD7iM7yOZUF5O7dfxNNvXZu5gZAYjwiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:39.333356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f393c48f1397de35931360e2027a01d61cb69e10fdb097fe25e5e492e18256ba","sha256:52cb7e669facdb5884866f252dd452332d70aa5f9d9c415fece397e09c46a32f"],"state_sha256":"c0052ce6a919ca3b555a8b3a3fd9e836acaa0151bb4b066b35a7bd712d9a5105"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UH8xVQhw/5DEavRdrCggrNImgpsWy10jShNavc1KaIl0ng7r3rQmbUOVurVajojy5RQtLbDUZsh4sWurrGJDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:20:09.922183Z","bundle_sha256":"87a7b7efb0d86edf037c904cb9333e1d02dc6811d4b8ceaadb183c91dacffc75"}}