{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T7G7NS3RGXH7PCOXNYUSK4HSM5","short_pith_number":"pith:T7G7NS3R","canonical_record":{"source":{"id":"2502.00964","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T00:04:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6d5f965b6ad409a1451e3a66fd0f086529f848ea95d53df940c0a02b868b0fa","abstract_canon_sha256":"58a1645772bd5814bd01fe5a01949e3dc1bd6b0b972c4e8b4b5aaa96f8d60953"},"schema_version":"1.0"},"canonical_sha256":"9fcdf6cb7135cff789d76e292570f2677a0121c42acfe3b3629ef4eb110ce157","source":{"kind":"arxiv","id":"2502.00964","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00964","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00964v3","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00964","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"T7G7NS3RGXH7","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"T7G7NS3RGXH7PCOX","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"T7G7NS3R","created_at":"2026-07-05T10:16:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T7G7NS3RGXH7PCOXNYUSK4HSM5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00964","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T00:04:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6d5f965b6ad409a1451e3a66fd0f086529f848ea95d53df940c0a02b868b0fa","abstract_canon_sha256":"58a1645772bd5814bd01fe5a01949e3dc1bd6b0b972c4e8b4b5aaa96f8d60953"},"schema_version":"1.0"},"canonical_sha256":"9fcdf6cb7135cff789d76e292570f2677a0121c42acfe3b3629ef4eb110ce157","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:41.279726Z","signature_b64":"i+5tKwPcP7LKHf4N2aqvrh3b3Ru7eIJhT0lk26mr89/rcbaWigf2P8bDxcp62b+yMYzIoE7Y8nepkc48EQj9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fcdf6cb7135cff789d76e292570f2677a0121c42acfe3b3629ef4eb110ce157","last_reissued_at":"2026-07-05T10:16:41.279231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:41.279231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00964","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAKotR/udxLYMKh9QVkYnSO0uf2aPxCkd3yp6TZ7U1aHyZ5h5iHtbAcvUVCO4ggDItrVH4thVxIbtVoZcIMKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T22:42:32.425102Z"},"content_sha256":"dc7d73879088ee6c66e727fac678b93d7d34c0154e1398228470484d93be2031","schema_version":"1.0","event_id":"sha256:dc7d73879088ee6c66e727fac678b93d7d34c0154e1398228470484d93be2031"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T7G7NS3RGXH7PCOXNYUSK4HSM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ML-Dev-Bench: Comparative Analysis of AI Agents on ML development workflows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chintan Shah, Dinkar Juyal, Harshith Padigela","submitted_at":"2025-02-03T00:04:49Z","abstract_excerpt":"In this report, we present ML-Dev-Bench, a benchmark aimed at testing agentic capabilities on applied Machine Learning development tasks. While existing benchmarks focus on isolated coding tasks or Kaggle-style competitions, ML-Dev-Bench tests agents' ability to handle the full complexity of ML development workflows. The benchmark assesses performance across critical aspects including dataset handling, model training, improving existing models, debugging, and API integration with popular ML tools. We evaluate three agents - ReAct, Openhands, and AIDE - on a diverse set of 30 tasks, providing i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00964","kind":"arxiv","version":3},"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/2502.00964/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":"2026-07-05T10:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nT+OCg7/MNh7Ekwo04OstmwaesChBXtK1WZuXigDmM8/kvVCywNwhLA90J4s2D/F05G3Z1BVzOGNhdl+m/auDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T22:42:32.425476Z"},"content_sha256":"68f30b3e445908eb8b45a184b41ebd6bd97541841d775b2073249c1a7fce942b","schema_version":"1.0","event_id":"sha256:68f30b3e445908eb8b45a184b41ebd6bd97541841d775b2073249c1a7fce942b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5/bundle.json","state_url":"https://pith.science/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5/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":"2026-07-25T22:42:32Z","links":{"resolver":"https://pith.science/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5","bundle":"https://pith.science/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5/bundle.json","state":"https://pith.science/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7G7NS3RGXH7PCOXNYUSK4HSM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T7G7NS3RGXH7PCOXNYUSK4HSM5","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":"58a1645772bd5814bd01fe5a01949e3dc1bd6b0b972c4e8b4b5aaa96f8d60953","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T00:04:49Z","title_canon_sha256":"f6d5f965b6ad409a1451e3a66fd0f086529f848ea95d53df940c0a02b868b0fa"},"schema_version":"1.0","source":{"id":"2502.00964","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00964","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00964v3","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00964","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"T7G7NS3RGXH7","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"T7G7NS3RGXH7PCOX","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"T7G7NS3R","created_at":"2026-07-05T10:16:41Z"}],"graph_snapshots":[{"event_id":"sha256:68f30b3e445908eb8b45a184b41ebd6bd97541841d775b2073249c1a7fce942b","target":"graph","created_at":"2026-07-05T10:16:41Z","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/2502.00964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this report, we present ML-Dev-Bench, a benchmark aimed at testing agentic capabilities on applied Machine Learning development tasks. While existing benchmarks focus on isolated coding tasks or Kaggle-style competitions, ML-Dev-Bench tests agents' ability to handle the full complexity of ML development workflows. The benchmark assesses performance across critical aspects including dataset handling, model training, improving existing models, debugging, and API integration with popular ML tools. We evaluate three agents - ReAct, Openhands, and AIDE - on a diverse set of 30 tasks, providing i","authors_text":"Chintan Shah, Dinkar Juyal, Harshith Padigela","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T00:04:49Z","title":"ML-Dev-Bench: Comparative Analysis of AI Agents on ML development workflows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00964","kind":"arxiv","version":3},"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:dc7d73879088ee6c66e727fac678b93d7d34c0154e1398228470484d93be2031","target":"record","created_at":"2026-07-05T10:16:41Z","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":"58a1645772bd5814bd01fe5a01949e3dc1bd6b0b972c4e8b4b5aaa96f8d60953","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T00:04:49Z","title_canon_sha256":"f6d5f965b6ad409a1451e3a66fd0f086529f848ea95d53df940c0a02b868b0fa"},"schema_version":"1.0","source":{"id":"2502.00964","kind":"arxiv","version":3}},"canonical_sha256":"9fcdf6cb7135cff789d76e292570f2677a0121c42acfe3b3629ef4eb110ce157","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fcdf6cb7135cff789d76e292570f2677a0121c42acfe3b3629ef4eb110ce157","first_computed_at":"2026-07-05T10:16:41.279231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:41.279231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+5tKwPcP7LKHf4N2aqvrh3b3Ru7eIJhT0lk26mr89/rcbaWigf2P8bDxcp62b+yMYzIoE7Y8nepkc48EQj9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:41.279726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00964","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc7d73879088ee6c66e727fac678b93d7d34c0154e1398228470484d93be2031","sha256:68f30b3e445908eb8b45a184b41ebd6bd97541841d775b2073249c1a7fce942b"],"state_sha256":"5786409cddd996a58f09bf18226b43a04d3ad79af9c458632cba9bfc3e1299b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T361OsPglTTCJqzEp/P3DWp827VjBpCm+9+tBFIoMokGNh94sNgh80cvrBDDLh8q3OgzUNLq9VhP7iV2SwqQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T22:42:32.427835Z","bundle_sha256":"6efa36a4328b6b12e4079bb42a83d9e2ffeebee9ed3697ac756601829bd554d6"}}