{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QFF7B4FRYIBVTWIGINT2W6V73S","short_pith_number":"pith:QFF7B4FR","canonical_record":{"source":{"id":"2310.03302","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T04:06:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"036bd98d60ff580620d7821765b2be87efb4f9ec050fe6182508713de161e0c2","abstract_canon_sha256":"8ca074a7f02fc8f8b430ecfd320a0f98cbb0a62349a7017e3cfc22388c554969"},"schema_version":"1.0"},"canonical_sha256":"814bf0f0b1c20359d9064367ab7abfdc95b0a4fcee08cc5c63cd84f76b4e8d08","source":{"kind":"arxiv","id":"2310.03302","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03302","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03302v2","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03302","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"pith_short_12","alias_value":"QFF7B4FRYIBV","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"pith_short_16","alias_value":"QFF7B4FRYIBVTWIG","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"pith_short_8","alias_value":"QFF7B4FR","created_at":"2026-07-05T08:07:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QFF7B4FRYIBVTWIGINT2W6V73S","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03302","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T04:06:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"036bd98d60ff580620d7821765b2be87efb4f9ec050fe6182508713de161e0c2","abstract_canon_sha256":"8ca074a7f02fc8f8b430ecfd320a0f98cbb0a62349a7017e3cfc22388c554969"},"schema_version":"1.0"},"canonical_sha256":"814bf0f0b1c20359d9064367ab7abfdc95b0a4fcee08cc5c63cd84f76b4e8d08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:58.475098Z","signature_b64":"WLlGxkvklWc2guTBi1fX1ONDKztZpmFKoFP0W4gaGw78Ljdll4rLgs9xTtKE8YXUlI/RGO4opOpwjgnZ3pZWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"814bf0f0b1c20359d9064367ab7abfdc95b0a4fcee08cc5c63cd84f76b4e8d08","last_reissued_at":"2026-07-05T08:07:58.474649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:58.474649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03302","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:07:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEXQgfFwYUIKT+Q9X7h+S9crRO57RO0II+mxp9gn01f6ePz1IjCKnn4E8P1Nhdo9nfjBR8S+zZNLImifzK/JDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T00:19:51.750811Z"},"content_sha256":"229eac1d59759b9f024bc7f9e39941a283064cfaf3e7c3dad7907ce5c8fc87e7","schema_version":"1.0","event_id":"sha256:229eac1d59759b9f024bc7f9e39941a283064cfaf3e7c3dad7907ce5c8fc87e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QFF7B4FRYIBVTWIGINT2W6V73S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jian Vora, Jure Leskovec, Percy Liang, Qian Huang","submitted_at":"2023-10-05T04:06:12Z","abstract_excerpt":"A central aspect of machine learning research is experimentation, the process of designing and running experiments, analyzing the results, and iterating towards some positive outcome (e.g., improving accuracy). Could agents driven by powerful language models perform machine learning experimentation effectively? To answer this question, we introduce MLAgentBench, a suite of 13 tasks ranging from improving model performance on CIFAR-10 to recent research problems like BabyLM. For each task, an agent can perform actions like reading/writing files, executing code, and inspecting outputs. We then c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03302","kind":"arxiv","version":2},"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/2310.03302/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":"2026-07-05T08:07:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8WP7/MphN8wFwxEbHbsYTeo3PSMdGX3rMbnkW2WjzoCRFnjT2xNqqUF6gNQkN5aDliVbv+g4hRdz6usSops6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T00:19:51.751199Z"},"content_sha256":"3e372141ff5ac804d5e4119ba0f6cedfa5def7b18cbc88cb0062fb016b5d2e20","schema_version":"1.0","event_id":"sha256:3e372141ff5ac804d5e4119ba0f6cedfa5def7b18cbc88cb0062fb016b5d2e20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFF7B4FRYIBVTWIGINT2W6V73S/bundle.json","state_url":"https://pith.science/pith/QFF7B4FRYIBVTWIGINT2W6V73S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFF7B4FRYIBVTWIGINT2W6V73S/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":"2026-07-16T00:19:51Z","links":{"resolver":"https://pith.science/pith/QFF7B4FRYIBVTWIGINT2W6V73S","bundle":"https://pith.science/pith/QFF7B4FRYIBVTWIGINT2W6V73S/bundle.json","state":"https://pith.science/pith/QFF7B4FRYIBVTWIGINT2W6V73S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFF7B4FRYIBVTWIGINT2W6V73S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QFF7B4FRYIBVTWIGINT2W6V73S","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":"8ca074a7f02fc8f8b430ecfd320a0f98cbb0a62349a7017e3cfc22388c554969","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T04:06:12Z","title_canon_sha256":"036bd98d60ff580620d7821765b2be87efb4f9ec050fe6182508713de161e0c2"},"schema_version":"1.0","source":{"id":"2310.03302","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03302","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03302v2","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03302","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"pith_short_12","alias_value":"QFF7B4FRYIBV","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"pith_short_16","alias_value":"QFF7B4FRYIBVTWIG","created_at":"2026-07-05T08:07:58Z"},{"alias_kind":"pith_short_8","alias_value":"QFF7B4FR","created_at":"2026-07-05T08:07:58Z"}],"graph_snapshots":[{"event_id":"sha256:3e372141ff5ac804d5e4119ba0f6cedfa5def7b18cbc88cb0062fb016b5d2e20","target":"graph","created_at":"2026-07-05T08:07:58Z","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/2310.03302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A central aspect of machine learning research is experimentation, the process of designing and running experiments, analyzing the results, and iterating towards some positive outcome (e.g., improving accuracy). Could agents driven by powerful language models perform machine learning experimentation effectively? To answer this question, we introduce MLAgentBench, a suite of 13 tasks ranging from improving model performance on CIFAR-10 to recent research problems like BabyLM. For each task, an agent can perform actions like reading/writing files, executing code, and inspecting outputs. We then c","authors_text":"Jian Vora, Jure Leskovec, Percy Liang, Qian Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T04:06:12Z","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03302","kind":"arxiv","version":2},"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":"sha256:229eac1d59759b9f024bc7f9e39941a283064cfaf3e7c3dad7907ce5c8fc87e7","target":"record","created_at":"2026-07-05T08:07:58Z","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":"8ca074a7f02fc8f8b430ecfd320a0f98cbb0a62349a7017e3cfc22388c554969","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T04:06:12Z","title_canon_sha256":"036bd98d60ff580620d7821765b2be87efb4f9ec050fe6182508713de161e0c2"},"schema_version":"1.0","source":{"id":"2310.03302","kind":"arxiv","version":2}},"canonical_sha256":"814bf0f0b1c20359d9064367ab7abfdc95b0a4fcee08cc5c63cd84f76b4e8d08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814bf0f0b1c20359d9064367ab7abfdc95b0a4fcee08cc5c63cd84f76b4e8d08","first_computed_at":"2026-07-05T08:07:58.474649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:58.474649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLlGxkvklWc2guTBi1fX1ONDKztZpmFKoFP0W4gaGw78Ljdll4rLgs9xTtKE8YXUlI/RGO4opOpwjgnZ3pZWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:58.475098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03302","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:229eac1d59759b9f024bc7f9e39941a283064cfaf3e7c3dad7907ce5c8fc87e7","sha256:3e372141ff5ac804d5e4119ba0f6cedfa5def7b18cbc88cb0062fb016b5d2e20"],"state_sha256":"03816910ddacf1051adfe5e682fc123b2cb2f13a591075f55f7fa5e9ad48b045"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Ag4AMkDBmOOCFS7GcapXRgm6qspRBckFCcYpTJdwltSXGLsaKFosW+rdrXa1dfAhY6LLDON1abDhXJh7qw5BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T00:19:51.753410Z","bundle_sha256":"246562547cdfd6007e3b05bd8788a9d7d5a5e486583760f33e7aa4134cc9868c"}}