{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RPVVU7CMBRXAGHP7DULNXCMJTL","short_pith_number":"pith:RPVVU7CM","canonical_record":{"source":{"id":"2409.00106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:43:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"ec836e7462c7b545cc4cb98daa0c33c23d1888177999d502d21d03839a3ccfb2","abstract_canon_sha256":"0738c4db8049fa97b435755699ad25cb575461f4e725135a3489b9df9bd032ce"},"schema_version":"1.0"},"canonical_sha256":"8beb5a7c4c0c6e031dff1d16db89899add5e3235dee1f06de8a0b60e52cf692d","source":{"kind":"arxiv","id":"2409.00106","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00106","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00106v1","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00106","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"pith_short_12","alias_value":"RPVVU7CMBRXA","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"pith_short_16","alias_value":"RPVVU7CMBRXAGHP7","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"pith_short_8","alias_value":"RPVVU7CM","created_at":"2026-07-05T09:01:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RPVVU7CMBRXAGHP7DULNXCMJTL","target":"record","payload":{"canonical_record":{"source":{"id":"2409.00106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:43:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"ec836e7462c7b545cc4cb98daa0c33c23d1888177999d502d21d03839a3ccfb2","abstract_canon_sha256":"0738c4db8049fa97b435755699ad25cb575461f4e725135a3489b9df9bd032ce"},"schema_version":"1.0"},"canonical_sha256":"8beb5a7c4c0c6e031dff1d16db89899add5e3235dee1f06de8a0b60e52cf692d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:40.989189Z","signature_b64":"AxSAV3SCr2gxnSpGBNLsmX7goocuHnuNAd1XlfwW4Nw0ZslB8v60nUMjsSH0A8vCggCbvmrjAWF3zLYKCYGNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8beb5a7c4c0c6e031dff1d16db89899add5e3235dee1f06de8a0b60e52cf692d","last_reissued_at":"2026-07-05T09:01:40.988747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:40.988747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.00106","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":"2026-07-05T09:01:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bUQ6E2tPmc3HUib/WIzzeWlbN2LIc4kZ4vLhDDAqeVZBSIH3MOiqdrEKGgSzXdllTxg2MCJF3swD1eT6WkdgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:52:20.381056Z"},"content_sha256":"35b4e2b74ab9f4de71435d23daf4c556679f11176de71a9c098327f2a1ae465a","schema_version":"1.0","event_id":"sha256:35b4e2b74ab9f4de71435d23daf4c556679f11176de71a9c098327f2a1ae465a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RPVVU7CMBRXAGHP7DULNXCMJTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aishik Nagar, Cheston Tan, Shantanu Jaiswal","submitted_at":"2024-08-27T14:43:54Z","abstract_excerpt":"Vision-language models (VLMs) have shown impressive zero- and few-shot performance on real-world visual question answering (VQA) benchmarks, alluding to their capabilities as visual reasoning engines. However, the benchmarks being used conflate \"pure\" visual reasoning with world knowledge, and also have questions that involve a limited number of reasoning steps. Thus, it remains unclear whether a VLM's apparent visual reasoning performance is due to its world knowledge, or due to actual visual reasoning capabilities.\n  To clarify this ambiguity, we systematically benchmark and dissect the zero"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00106","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/2409.00106/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":"2026-07-05T09:01:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ATtPpD4MfG5P6IRlPYM7MCaKxHyIoWqDsZK3OQ18Fvv//+M8VJVoOJITISxY8L2d3V1odVwdnGRiHdG+/BevAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:52:20.381582Z"},"content_sha256":"336d0bf00984cc9fca7b7fd5602d6ad6b12ee41e54d11e1b16750f02013066f3","schema_version":"1.0","event_id":"sha256:336d0bf00984cc9fca7b7fd5602d6ad6b12ee41e54d11e1b16750f02013066f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPVVU7CMBRXAGHP7DULNXCMJTL/bundle.json","state_url":"https://pith.science/pith/RPVVU7CMBRXAGHP7DULNXCMJTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPVVU7CMBRXAGHP7DULNXCMJTL/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":"2026-08-15T16:52:20Z","links":{"resolver":"https://pith.science/pith/RPVVU7CMBRXAGHP7DULNXCMJTL","bundle":"https://pith.science/pith/RPVVU7CMBRXAGHP7DULNXCMJTL/bundle.json","state":"https://pith.science/pith/RPVVU7CMBRXAGHP7DULNXCMJTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPVVU7CMBRXAGHP7DULNXCMJTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPVVU7CMBRXAGHP7DULNXCMJTL","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":"0738c4db8049fa97b435755699ad25cb575461f4e725135a3489b9df9bd032ce","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:43:54Z","title_canon_sha256":"ec836e7462c7b545cc4cb98daa0c33c23d1888177999d502d21d03839a3ccfb2"},"schema_version":"1.0","source":{"id":"2409.00106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00106","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00106v1","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00106","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"pith_short_12","alias_value":"RPVVU7CMBRXA","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"pith_short_16","alias_value":"RPVVU7CMBRXAGHP7","created_at":"2026-07-05T09:01:40Z"},{"alias_kind":"pith_short_8","alias_value":"RPVVU7CM","created_at":"2026-07-05T09:01:40Z"}],"graph_snapshots":[{"event_id":"sha256:336d0bf00984cc9fca7b7fd5602d6ad6b12ee41e54d11e1b16750f02013066f3","target":"graph","created_at":"2026-07-05T09:01:40Z","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/2409.00106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have shown impressive zero- and few-shot performance on real-world visual question answering (VQA) benchmarks, alluding to their capabilities as visual reasoning engines. However, the benchmarks being used conflate \"pure\" visual reasoning with world knowledge, and also have questions that involve a limited number of reasoning steps. Thus, it remains unclear whether a VLM's apparent visual reasoning performance is due to its world knowledge, or due to actual visual reasoning capabilities.\n  To clarify this ambiguity, we systematically benchmark and dissect the zero","authors_text":"Aishik Nagar, Cheston Tan, Shantanu Jaiswal","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:43:54Z","title":"Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00106","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":"sha256:35b4e2b74ab9f4de71435d23daf4c556679f11176de71a9c098327f2a1ae465a","target":"record","created_at":"2026-07-05T09:01:40Z","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":"0738c4db8049fa97b435755699ad25cb575461f4e725135a3489b9df9bd032ce","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:43:54Z","title_canon_sha256":"ec836e7462c7b545cc4cb98daa0c33c23d1888177999d502d21d03839a3ccfb2"},"schema_version":"1.0","source":{"id":"2409.00106","kind":"arxiv","version":1}},"canonical_sha256":"8beb5a7c4c0c6e031dff1d16db89899add5e3235dee1f06de8a0b60e52cf692d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8beb5a7c4c0c6e031dff1d16db89899add5e3235dee1f06de8a0b60e52cf692d","first_computed_at":"2026-07-05T09:01:40.988747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:40.988747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AxSAV3SCr2gxnSpGBNLsmX7goocuHnuNAd1XlfwW4Nw0ZslB8v60nUMjsSH0A8vCggCbvmrjAWF3zLYKCYGNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:40.989189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35b4e2b74ab9f4de71435d23daf4c556679f11176de71a9c098327f2a1ae465a","sha256:336d0bf00984cc9fca7b7fd5602d6ad6b12ee41e54d11e1b16750f02013066f3"],"state_sha256":"e0a07468080d7021d6278ec81b71f5db7733e95060000d5a067f628a61f5a85e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1eC+8gcvuhJPqb4W6Njttvy5sxO6hvMU+ECluj6t7roHPO9fLcPdASJApsiDtjj3ftRxxmrGvKkNsx93lcWgCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:52:20.387422Z","bundle_sha256":"21cd4d01b02548d71aee4f8bd17e8d2a00d102a7ea52433bc4b0f541ba64bc13"}}