{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KYQOPQBG42HNBOQOVSUI2WLNSM","short_pith_number":"pith:KYQOPQBG","canonical_record":{"source":{"id":"2403.11085","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T04:36:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ee56b7e58e340285a682d8cae6488d8ef0ac533f9d1acad0953bbf5c71a8fcd2","abstract_canon_sha256":"2f91b318dd6a334fc52f008051ddd86522ba91c25762a92ac4a7f4f509d23713"},"schema_version":"1.0"},"canonical_sha256":"5620e7c026e68ed0ba0eaca88d596d9339b4eada0ed869b0b924724d74a6627d","source":{"kind":"arxiv","id":"2403.11085","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KYQOPQBG42HNBOQOVSUI2WLNSM","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11085","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T04:36:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ee56b7e58e340285a682d8cae6488d8ef0ac533f9d1acad0953bbf5c71a8fcd2","abstract_canon_sha256":"2f91b318dd6a334fc52f008051ddd86522ba91c25762a92ac4a7f4f509d23713"},"schema_version":"1.0"},"canonical_sha256":"5620e7c026e68ed0ba0eaca88d596d9339b4eada0ed869b0b924724d74a6627d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:57.431673Z","signature_b64":"y25WpdbHgu7zm8fCBVCGhlJ2XmEbTi/+bfFjJc7kIZZIn756kxhYbIOT9v3j4LUNB0gL3WQ5v0bFK+4wb3p5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5620e7c026e68ed0ba0eaca88d596d9339b4eada0ed869b0b924724d74a6627d","last_reissued_at":"2026-07-05T09:09:57.431189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:57.431189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11085","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+VRpG4mcRvuR5kF7qzHLzXgU+RaGBMi5M1VViHgOfbbzS8RIPRdvH9syc3IaFPnAa56rek0n11rVWQI65CdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:07:22.284717Z"},"content_sha256":"bad8e59f0bd3e8631eecf45d54caa0173a4948eedec6ebffd944c17bbfe39da5","schema_version":"1.0","event_id":"sha256:bad8e59f0bd3e8631eecf45d54caa0173a4948eedec6ebffd944c17bbfe39da5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KYQOPQBG42HNBOQOVSUI2WLNSM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jieyu Zhang, Ranjay Krishna, Tanmay Gupta, Weikai Huang, Zixian Ma","submitted_at":"2024-03-17T04:36:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11085","kind":"arxiv","version":4},"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/2403.11085/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":"2026-07-05T09:09:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMf8JUU/yd2cdEBE1HxJzmoVrpbAJsXMKZfDKxlnSZCfdeCtFQ7ywXeSH3BhhvkZztmm8K1DCxTL9c9j6bqDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:07:22.285239Z"},"content_sha256":"fbc3cc64bde21e11cfe7121a8585b593df84869baa655aa64e879c93b9f2e963","schema_version":"1.0","event_id":"sha256:fbc3cc64bde21e11cfe7121a8585b593df84869baa655aa64e879c93b9f2e963"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYQOPQBG42HNBOQOVSUI2WLNSM/bundle.json","state_url":"https://pith.science/pith/KYQOPQBG42HNBOQOVSUI2WLNSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYQOPQBG42HNBOQOVSUI2WLNSM/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":"2026-08-16T07:07:22Z","links":{"resolver":"https://pith.science/pith/KYQOPQBG42HNBOQOVSUI2WLNSM","bundle":"https://pith.science/pith/KYQOPQBG42HNBOQOVSUI2WLNSM/bundle.json","state":"https://pith.science/pith/KYQOPQBG42HNBOQOVSUI2WLNSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYQOPQBG42HNBOQOVSUI2WLNSM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ec/QQ5UrULZLPGz8phYOG+DAw330jkgg8b99b3DsnUx9ggonco6Dp3pyZZ0k9uGbVS9JAwDyZdmjsVNdkALCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:07:22.290467Z","bundle_sha256":"ce8d0f26a1dc05ce868f15992c60fa713ef96be3daab027bfe9a49c4bc2ce556"}}