{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YJNKQYRKRADT3UOWMPS2T4536O","short_pith_number":"pith:YJNKQYRK","canonical_record":{"source":{"id":"2408.02210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T03:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"3789487f643c95d94a9922f09a7a9f65d791f4464d1238a57849a50b2f776f89","abstract_canon_sha256":"b9a22cff25caf8eb6dfeaa1f48dbf0166c6ea282abf95fc221658385afece3b1"},"schema_version":"1.0"},"canonical_sha256":"c25aa8622a88073dd1d663e5a9f3bbf3b43a29d127fa049ba6cce765cef1d5ad","source":{"kind":"arxiv","id":"2408.02210","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02210","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02210v1","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02210","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"YJNKQYRKRADT","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"YJNKQYRKRADT3UOW","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"YJNKQYRK","created_at":"2026-07-05T08:52:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YJNKQYRKRADT3UOWMPS2T4536O","target":"record","payload":{"canonical_record":{"source":{"id":"2408.02210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T03:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"3789487f643c95d94a9922f09a7a9f65d791f4464d1238a57849a50b2f776f89","abstract_canon_sha256":"b9a22cff25caf8eb6dfeaa1f48dbf0166c6ea282abf95fc221658385afece3b1"},"schema_version":"1.0"},"canonical_sha256":"c25aa8622a88073dd1d663e5a9f3bbf3b43a29d127fa049ba6cce765cef1d5ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:09.050457Z","signature_b64":"vl5Otm8NFH2UEFnTeEtPUuPTDn9iw0w75OMlP4ihR31NBIINsSytqfYCJeC8/pfzWTO7zkb0p90SmtwBKx3uDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c25aa8622a88073dd1d663e5a9f3bbf3b43a29d127fa049ba6cce765cef1d5ad","last_reissued_at":"2026-07-05T08:52:09.050120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:09.050120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.02210","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":"2026-07-05T08:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8p3NfaX3C3zwpGYCRHAixWS97PNA0tUvD0SS1zKZ5uo8kWKsjeZmSMUCc5f27uQ1d1p4qroWB+ont1zLy9BRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:54:12.823846Z"},"content_sha256":"74be4b5ae43a659fc560521af0a03aacb3b7aeb6650181c71eade90cd4535d72","schema_version":"1.0","event_id":"sha256:74be4b5ae43a659fc560521af0a03aacb3b7aeb6650181c71eade90cd4535d72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YJNKQYRKRADT3UOWMPS2T4536O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Yuxuan Wang, Zhuowan Li, Zilong Zheng","submitted_at":"2024-08-05T03:22:10Z","abstract_excerpt":"Compositional visual reasoning methods, which translate a complex query into a structured composition of feasible visual tasks, have exhibited a strong potential in complicated multi-modal tasks. Empowered by recent advances in large language models (LLMs), this multi-modal challenge has been brought to a new stage by treating LLMs as few-shot/zero-shot planners, i.e., vision-language (VL) programming. Such methods, despite their numerous merits, suffer from challenges due to LLM planning mistakes or inaccuracy of visual execution modules, lagging behind the non-compositional models. In this w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02210","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/2408.02210/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":"2026-07-05T08:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IXbGDlWsYSv56eYemh60ztPa+zbQymKf8uPZBOjKfjJ/mSqatIvLhZ/kbBhICqMwDzMUJAATtqK2H0CJfQHbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:54:12.824805Z"},"content_sha256":"04a42d8ca8b0453d839b27ca5738059a07c122b558aee29042a567fbebe8c591","schema_version":"1.0","event_id":"sha256:04a42d8ca8b0453d839b27ca5738059a07c122b558aee29042a567fbebe8c591"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJNKQYRKRADT3UOWMPS2T4536O/bundle.json","state_url":"https://pith.science/pith/YJNKQYRKRADT3UOWMPS2T4536O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJNKQYRKRADT3UOWMPS2T4536O/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":"2026-08-09T20:54:12Z","links":{"resolver":"https://pith.science/pith/YJNKQYRKRADT3UOWMPS2T4536O","bundle":"https://pith.science/pith/YJNKQYRKRADT3UOWMPS2T4536O/bundle.json","state":"https://pith.science/pith/YJNKQYRKRADT3UOWMPS2T4536O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJNKQYRKRADT3UOWMPS2T4536O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJNKQYRKRADT3UOWMPS2T4536O","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":"b9a22cff25caf8eb6dfeaa1f48dbf0166c6ea282abf95fc221658385afece3b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T03:22:10Z","title_canon_sha256":"3789487f643c95d94a9922f09a7a9f65d791f4464d1238a57849a50b2f776f89"},"schema_version":"1.0","source":{"id":"2408.02210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02210","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02210v1","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02210","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"YJNKQYRKRADT","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"YJNKQYRKRADT3UOW","created_at":"2026-07-05T08:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"YJNKQYRK","created_at":"2026-07-05T08:52:09Z"}],"graph_snapshots":[{"event_id":"sha256:04a42d8ca8b0453d839b27ca5738059a07c122b558aee29042a567fbebe8c591","target":"graph","created_at":"2026-07-05T08:52:09Z","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/2408.02210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional visual reasoning methods, which translate a complex query into a structured composition of feasible visual tasks, have exhibited a strong potential in complicated multi-modal tasks. Empowered by recent advances in large language models (LLMs), this multi-modal challenge has been brought to a new stage by treating LLMs as few-shot/zero-shot planners, i.e., vision-language (VL) programming. Such methods, despite their numerous merits, suffer from challenges due to LLM planning mistakes or inaccuracy of visual execution modules, lagging behind the non-compositional models. In this w","authors_text":"Alan Yuille, Yuxuan Wang, Zhuowan Li, Zilong Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T03:22:10Z","title":"ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02210","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":"sha256:74be4b5ae43a659fc560521af0a03aacb3b7aeb6650181c71eade90cd4535d72","target":"record","created_at":"2026-07-05T08:52:09Z","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":"b9a22cff25caf8eb6dfeaa1f48dbf0166c6ea282abf95fc221658385afece3b1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T03:22:10Z","title_canon_sha256":"3789487f643c95d94a9922f09a7a9f65d791f4464d1238a57849a50b2f776f89"},"schema_version":"1.0","source":{"id":"2408.02210","kind":"arxiv","version":1}},"canonical_sha256":"c25aa8622a88073dd1d663e5a9f3bbf3b43a29d127fa049ba6cce765cef1d5ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c25aa8622a88073dd1d663e5a9f3bbf3b43a29d127fa049ba6cce765cef1d5ad","first_computed_at":"2026-07-05T08:52:09.050120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:09.050120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vl5Otm8NFH2UEFnTeEtPUuPTDn9iw0w75OMlP4ihR31NBIINsSytqfYCJeC8/pfzWTO7zkb0p90SmtwBKx3uDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:09.050457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74be4b5ae43a659fc560521af0a03aacb3b7aeb6650181c71eade90cd4535d72","sha256:04a42d8ca8b0453d839b27ca5738059a07c122b558aee29042a567fbebe8c591"],"state_sha256":"14d726dee578348b7374c50109341f9822e6a743318812ef0475059e00585dd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ruEPAL4jXUsFO6LM3ftiR6R3P8RfkVVymRDTFi7QjIsnSF3gQcgTs1jaNra4nJb/8owXe5upQT3VLdG1Pr4AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:54:12.830631Z","bundle_sha256":"4cabd01033877dc8e783057faa07df98c8aad3c225467fa8e8c036c6c1cdaa83"}}