{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CMFLGHS7SBDTHUIGHAYFXRVNTG","short_pith_number":"pith:CMFLGHS7","canonical_record":{"source":{"id":"2506.00794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T02:46:31Z","cross_cats_sorted":[],"title_canon_sha256":"87a6e33d9d7e0596221d618569aba8c86c430c8b6bd8c04f20688c76b054b32b","abstract_canon_sha256":"1969f4c5346c9d9eba1d71ab09591e60fb0e42a5bb46bc59e63585a91a07d0b7"},"schema_version":"1.0"},"canonical_sha256":"130ab31e5f904733d10638305bc6ad99b570c23a6da0baec61ac14d630d5acbb","source":{"kind":"arxiv","id":"2506.00794","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00794","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00794v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00794","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"CMFLGHS7SBDT","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"CMFLGHS7SBDTHUIG","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"CMFLGHS7","created_at":"2026-07-05T11:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CMFLGHS7SBDTHUIGHAYFXRVNTG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T02:46:31Z","cross_cats_sorted":[],"title_canon_sha256":"87a6e33d9d7e0596221d618569aba8c86c430c8b6bd8c04f20688c76b054b32b","abstract_canon_sha256":"1969f4c5346c9d9eba1d71ab09591e60fb0e42a5bb46bc59e63585a91a07d0b7"},"schema_version":"1.0"},"canonical_sha256":"130ab31e5f904733d10638305bc6ad99b570c23a6da0baec61ac14d630d5acbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:40.560569Z","signature_b64":"V2kepj8NvvQ4POIY1hI/fBFDsfQl/QugWeo9G8NZtuD6KN+DP0ylhD9o7VeuTccQPZ9owL0yQ3Kfh3LvNyZOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130ab31e5f904733d10638305bc6ad99b570c23a6da0baec61ac14d630d5acbb","last_reissued_at":"2026-07-05T11:13:40.560104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:40.560104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00794","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":"2026-07-05T11:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/HOqaBWp8/YZ7nfOm7En4/noGo6DyqnMIpHcV1qx1K0ZpqXAq4wwNZUpX64xK/Tr0eCkPBibDGCaxYctOF5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:36:46.095763Z"},"content_sha256":"8694394f6fd61a2c61fde54e83c611a11c478aa45de8783a140f53a654f9e7cf","schema_version":"1.0","event_id":"sha256:8694394f6fd61a2c61fde54e83c611a11c478aa45de8783a140f53a654f9e7cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CMFLGHS7SBDTHUIGHAYFXRVNTG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting Empirical AI Research Outcomes with Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenglei Si, He He, Jiaxin Wen, Shi Feng, Yueh-han Chen","submitted_at":"2025-06-01T02:46:31Z","abstract_excerpt":"Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even expert researchers can only acquire through substantial experience. We build the first benchmark for this task and compare LMs with human experts. Concretely, given two research ideas (e.g., two jailbreaking methods), we aim to predict which will perform better on a set of benchmarks. We scrape ideas and experimental results from conference papers, yielding 1,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00794","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/2506.00794/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":"2026-07-05T11:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neVxYP4/Hmsk/wr14Q+T6Thf/jJfI7YkpMZSZrfgt7yLR9mqJp2zLaxMLrz/UW1lZehYiWYxzyJ/v+n0q7lXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:36:46.096605Z"},"content_sha256":"aeac968297fdd9bbe0bf718eafc6f0b66f1ca780dd14265e1266c568b75e01e4","schema_version":"1.0","event_id":"sha256:aeac968297fdd9bbe0bf718eafc6f0b66f1ca780dd14265e1266c568b75e01e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG/bundle.json","state_url":"https://pith.science/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG/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":"2026-08-07T22:36:46Z","links":{"resolver":"https://pith.science/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG","bundle":"https://pith.science/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG/bundle.json","state":"https://pith.science/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMFLGHS7SBDTHUIGHAYFXRVNTG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CMFLGHS7SBDTHUIGHAYFXRVNTG","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":"1969f4c5346c9d9eba1d71ab09591e60fb0e42a5bb46bc59e63585a91a07d0b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T02:46:31Z","title_canon_sha256":"87a6e33d9d7e0596221d618569aba8c86c430c8b6bd8c04f20688c76b054b32b"},"schema_version":"1.0","source":{"id":"2506.00794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00794","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00794v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00794","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"CMFLGHS7SBDT","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"CMFLGHS7SBDTHUIG","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"CMFLGHS7","created_at":"2026-07-05T11:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:aeac968297fdd9bbe0bf718eafc6f0b66f1ca780dd14265e1266c568b75e01e4","target":"graph","created_at":"2026-07-05T11:13:40Z","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/2506.00794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even expert researchers can only acquire through substantial experience. We build the first benchmark for this task and compare LMs with human experts. Concretely, given two research ideas (e.g., two jailbreaking methods), we aim to predict which will perform better on a set of benchmarks. We scrape ideas and experimental results from conference papers, yielding 1,","authors_text":"Chenglei Si, He He, Jiaxin Wen, Shi Feng, Yueh-han Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T02:46:31Z","title":"Predicting Empirical AI Research Outcomes with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00794","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":"sha256:8694394f6fd61a2c61fde54e83c611a11c478aa45de8783a140f53a654f9e7cf","target":"record","created_at":"2026-07-05T11:13:40Z","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":"1969f4c5346c9d9eba1d71ab09591e60fb0e42a5bb46bc59e63585a91a07d0b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-01T02:46:31Z","title_canon_sha256":"87a6e33d9d7e0596221d618569aba8c86c430c8b6bd8c04f20688c76b054b32b"},"schema_version":"1.0","source":{"id":"2506.00794","kind":"arxiv","version":1}},"canonical_sha256":"130ab31e5f904733d10638305bc6ad99b570c23a6da0baec61ac14d630d5acbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"130ab31e5f904733d10638305bc6ad99b570c23a6da0baec61ac14d630d5acbb","first_computed_at":"2026-07-05T11:13:40.560104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:40.560104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V2kepj8NvvQ4POIY1hI/fBFDsfQl/QugWeo9G8NZtuD6KN+DP0ylhD9o7VeuTccQPZ9owL0yQ3Kfh3LvNyZOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:40.560569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8694394f6fd61a2c61fde54e83c611a11c478aa45de8783a140f53a654f9e7cf","sha256:aeac968297fdd9bbe0bf718eafc6f0b66f1ca780dd14265e1266c568b75e01e4"],"state_sha256":"2bb351110c1148664a5ed646493fb2a513a9bd234c34d48663f0b8380e795aa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P18dhRa6xTVHH6KSFGa6jVepeI+vVj6z9HqfmWnqZPi1SMkccxdNywJoENLdngcOJNAASe+RbVYWU8TW2QeZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:36:46.102604Z","bundle_sha256":"d00b292e08776ec5b451ee3de6554a6924446d20a0cd7d5c8c64440073f665bd"}}