{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KYQOPQBG42HNBOQOVSUI2WLNSM","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":"2f91b318dd6a334fc52f008051ddd86522ba91c25762a92ac4a7f4f509d23713","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T04:36:18Z","title_canon_sha256":"ee56b7e58e340285a682d8cae6488d8ef0ac533f9d1acad0953bbf5c71a8fcd2"},"schema_version":"1.0","source":{"id":"2403.11085","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11085","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11085v4","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11085","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"pith_short_12","alias_value":"KYQOPQBG42HN","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"pith_short_16","alias_value":"KYQOPQBG42HNBOQO","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"pith_short_8","alias_value":"KYQOPQBG","created_at":"2026-07-05T09:09:57Z"}],"graph_snapshots":[{"event_id":"sha256:fbc3cc64bde21e11cfe7121a8585b593df84869baa655aa64e879c93b9f2e963","target":"graph","created_at":"2026-07-05T09:09:57Z","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/2403.11085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world multi-modal problems are rarely solved by a single machine learning model, and often require multi-step computational plans that involve stitching several models. Tool-augmented LLMs hold tremendous promise for automating the generation of such computational plans. However, the lack of standardized benchmarks for evaluating LLMs as planners for multi-step multi-modal tasks has prevented a systematic study of planner design decisions. Should LLMs generate a full plan in a single shot or step-by-step? Should they invoke tools directly with Python code or through structured data format","authors_text":"Jieyu Zhang, Ranjay Krishna, Tanmay Gupta, Weikai Huang, Zixian Ma","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T04:36:18Z","title":"m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11085","kind":"arxiv","version":4},"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:bad8e59f0bd3e8631eecf45d54caa0173a4948eedec6ebffd944c17bbfe39da5","target":"record","created_at":"2026-07-05T09:09:57Z","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":"2f91b318dd6a334fc52f008051ddd86522ba91c25762a92ac4a7f4f509d23713","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T04:36:18Z","title_canon_sha256":"ee56b7e58e340285a682d8cae6488d8ef0ac533f9d1acad0953bbf5c71a8fcd2"},"schema_version":"1.0","source":{"id":"2403.11085","kind":"arxiv","version":4}},"canonical_sha256":"5620e7c026e68ed0ba0eaca88d596d9339b4eada0ed869b0b924724d74a6627d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5620e7c026e68ed0ba0eaca88d596d9339b4eada0ed869b0b924724d74a6627d","first_computed_at":"2026-07-05T09:09:57.431189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:57.431189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y25WpdbHgu7zm8fCBVCGhlJ2XmEbTi/+bfFjJc7kIZZIn756kxhYbIOT9v3j4LUNB0gL3WQ5v0bFK+4wb3p5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:57.431673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11085","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bad8e59f0bd3e8631eecf45d54caa0173a4948eedec6ebffd944c17bbfe39da5","sha256:fbc3cc64bde21e11cfe7121a8585b593df84869baa655aa64e879c93b9f2e963"],"state_sha256":"fff663804778df1b70a477904e6bc069356f25f656558efda7a3a2647823117d"}