{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OLSR3BJANO2O7IY6R7N62JNKCL","short_pith_number":"pith:OLSR3BJA","canonical_record":{"source":{"id":"2506.01578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:07:11Z","cross_cats_sorted":[],"title_canon_sha256":"1d76cdc636ffa164310722b8bb0a3e641fe2332103684165ae6881b93f98e68b","abstract_canon_sha256":"666a7c4c266e86c8c0f5c81ff0bc6a882710d6559d61b5d580b9020f7cbc54c7"},"schema_version":"1.0"},"canonical_sha256":"72e51d85206bb4efa31e8fdbed25aa12e63e5803374e81a7ccde05c3103b829b","source":{"kind":"arxiv","id":"2506.01578","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01578","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01578v1","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01578","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"OLSR3BJANO2O","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"OLSR3BJANO2O7IY6","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"OLSR3BJA","created_at":"2026-07-05T11:14:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OLSR3BJANO2O7IY6R7N62JNKCL","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:07:11Z","cross_cats_sorted":[],"title_canon_sha256":"1d76cdc636ffa164310722b8bb0a3e641fe2332103684165ae6881b93f98e68b","abstract_canon_sha256":"666a7c4c266e86c8c0f5c81ff0bc6a882710d6559d61b5d580b9020f7cbc54c7"},"schema_version":"1.0"},"canonical_sha256":"72e51d85206bb4efa31e8fdbed25aa12e63e5803374e81a7ccde05c3103b829b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:16.161274Z","signature_b64":"BrurHJdUKhG91/N9bpDNqxiE5mJ9NjiJvmEW8RSJ5N+TOIdLlzkHPi/G6LZO2xIV1LmKkzi6P+qwzk5CNp5DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72e51d85206bb4efa31e8fdbed25aa12e63e5803374e81a7ccde05c3103b829b","last_reissued_at":"2026-07-05T11:14:16.160840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:16.160840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01578","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":"2026-07-05T11:14:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9dBey5jjy6fqY0qD3ZR5LCLN+BbItyY5/EpEEn9bM8tsi0MIH0YAPpU4E8ifv+1BfMvGr0iVncmjyhJvAWEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:49:21.539603Z"},"content_sha256":"771324dfd14da08ca9d557704f5c859c830cbb27b245272b265fd03de68f66f5","schema_version":"1.0","event_id":"sha256:771324dfd14da08ca9d557704f5c859c830cbb27b245272b265fd03de68f66f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OLSR3BJANO2O7IY6R7N62JNKCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompt Engineering Large Language Models' Forecasting Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Mellers, Cameron R. Jones, Philip E. Tetlock, Philipp Schoenegger","submitted_at":"2025-06-02T12:07:11Z","abstract_excerpt":"Large language model performance can be improved in a large number of ways. Many such techniques, like fine-tuning or advanced tool usage, are time-intensive and expensive. Although prompt engineering is significantly cheaper and often works for simpler tasks, it remains unclear whether prompt engineering suffices for more complex domains like forecasting. Here we show that small prompt modifications rarely boost forecasting accuracy beyond a minimal baseline. In our first study, we tested 38 prompts across Claude 3.5 Sonnet, Claude 3.5 Haiku, GPT-4o, and Llama 3.1 405B. In our second, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01578","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/2506.01578/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":"2026-07-05T11:14:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0bcZGAdm3zsnHLj0W/CTEnjT5Xrhi24oZdF9LmxFgKVi+OzTtuRnaFzw6gY82ye59SB/k4XvmyHcZ/TXDmaSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:49:21.540094Z"},"content_sha256":"293cc375c23743f6a112c979760757c192c12af0a062af9105e6f224fe140e90","schema_version":"1.0","event_id":"sha256:293cc375c23743f6a112c979760757c192c12af0a062af9105e6f224fe140e90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OLSR3BJANO2O7IY6R7N62JNKCL/bundle.json","state_url":"https://pith.science/pith/OLSR3BJANO2O7IY6R7N62JNKCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OLSR3BJANO2O7IY6R7N62JNKCL/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":"2026-08-08T08:49:21Z","links":{"resolver":"https://pith.science/pith/OLSR3BJANO2O7IY6R7N62JNKCL","bundle":"https://pith.science/pith/OLSR3BJANO2O7IY6R7N62JNKCL/bundle.json","state":"https://pith.science/pith/OLSR3BJANO2O7IY6R7N62JNKCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OLSR3BJANO2O7IY6R7N62JNKCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OLSR3BJANO2O7IY6R7N62JNKCL","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":"666a7c4c266e86c8c0f5c81ff0bc6a882710d6559d61b5d580b9020f7cbc54c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:07:11Z","title_canon_sha256":"1d76cdc636ffa164310722b8bb0a3e641fe2332103684165ae6881b93f98e68b"},"schema_version":"1.0","source":{"id":"2506.01578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01578","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01578v1","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01578","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"OLSR3BJANO2O","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"OLSR3BJANO2O7IY6","created_at":"2026-07-05T11:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"OLSR3BJA","created_at":"2026-07-05T11:14:16Z"}],"graph_snapshots":[{"event_id":"sha256:293cc375c23743f6a112c979760757c192c12af0a062af9105e6f224fe140e90","target":"graph","created_at":"2026-07-05T11:14:16Z","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/2506.01578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model performance can be improved in a large number of ways. Many such techniques, like fine-tuning or advanced tool usage, are time-intensive and expensive. Although prompt engineering is significantly cheaper and often works for simpler tasks, it remains unclear whether prompt engineering suffices for more complex domains like forecasting. Here we show that small prompt modifications rarely boost forecasting accuracy beyond a minimal baseline. In our first study, we tested 38 prompts across Claude 3.5 Sonnet, Claude 3.5 Haiku, GPT-4o, and Llama 3.1 405B. In our second, we intr","authors_text":"Barbara Mellers, Cameron R. Jones, Philip E. Tetlock, Philipp Schoenegger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:07:11Z","title":"Prompt Engineering Large Language Models' Forecasting Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01578","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":"sha256:771324dfd14da08ca9d557704f5c859c830cbb27b245272b265fd03de68f66f5","target":"record","created_at":"2026-07-05T11:14:16Z","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":"666a7c4c266e86c8c0f5c81ff0bc6a882710d6559d61b5d580b9020f7cbc54c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:07:11Z","title_canon_sha256":"1d76cdc636ffa164310722b8bb0a3e641fe2332103684165ae6881b93f98e68b"},"schema_version":"1.0","source":{"id":"2506.01578","kind":"arxiv","version":1}},"canonical_sha256":"72e51d85206bb4efa31e8fdbed25aa12e63e5803374e81a7ccde05c3103b829b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72e51d85206bb4efa31e8fdbed25aa12e63e5803374e81a7ccde05c3103b829b","first_computed_at":"2026-07-05T11:14:16.160840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:16.160840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BrurHJdUKhG91/N9bpDNqxiE5mJ9NjiJvmEW8RSJ5N+TOIdLlzkHPi/G6LZO2xIV1LmKkzi6P+qwzk5CNp5DDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:16.161274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:771324dfd14da08ca9d557704f5c859c830cbb27b245272b265fd03de68f66f5","sha256:293cc375c23743f6a112c979760757c192c12af0a062af9105e6f224fe140e90"],"state_sha256":"b3bf473d1bffbe40c433e763a965d5b92c587bc604f6653878cf7abf80477c9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUpw988NahF9ODOoLWgtNzTSVDkbOAjPc4u6yc4sbvIceXLwi1iclv+RJBL75KBmkWItpf3lMEBgPqitSLI1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:49:21.544733Z","bundle_sha256":"38685fc68f66ca84060f114ed5f8f3180052433075b6964173c4cd5b2990318e"}}