{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:53X3API7VYK6UGU4OOHQHJQTSB","short_pith_number":"pith:53X3API7","canonical_record":{"source":{"id":"2505.20021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T14:09:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7bb13e8b3206edb7ee62399922a54bfe580ee0416f7a4a8f31c7b09811b61c47","abstract_canon_sha256":"116eb87bdc03800bcb0485832f351e9c4193210ae5d8554b25f197c3ee611345"},"schema_version":"1.0"},"canonical_sha256":"eeefb03d1fae15ea1a9c738f03a613904d3cbd36589d3905f6f45ae97bca7fbf","source":{"kind":"arxiv","id":"2505.20021","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20021","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20021v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20021","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"53X3API7VYK6","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"53X3API7VYK6UGU4","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"53X3API7","created_at":"2026-07-05T11:09:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:53X3API7VYK6UGU4OOHQHJQTSB","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T14:09:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7bb13e8b3206edb7ee62399922a54bfe580ee0416f7a4a8f31c7b09811b61c47","abstract_canon_sha256":"116eb87bdc03800bcb0485832f351e9c4193210ae5d8554b25f197c3ee611345"},"schema_version":"1.0"},"canonical_sha256":"eeefb03d1fae15ea1a9c738f03a613904d3cbd36589d3905f6f45ae97bca7fbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:51.388090Z","signature_b64":"Erld07U7e775KpQ0lFE+Fgf69/+DmAgshhnuR/sTOuZVeHZ6p3xb04HVZmNA3yc4GJ2U9JiYoZr1/0xTRbRtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeefb03d1fae15ea1a9c738f03a613904d3cbd36589d3905f6f45ae97bca7fbf","last_reissued_at":"2026-07-05T11:09:51.387600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:51.387600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20021","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":"2026-07-05T11:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OsRUafHSBW19ToAJidK12UYdsEhi9fnp7b6s8Tayhg8xrJorM97E5T/6pXKpE1dvdcVc9PhjwhW8db0SdfZMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:35:46.057673Z"},"content_sha256":"7a63aa6ba9b2daf8662d3bbdb22f037383372a6bf0870c15fae4eecc0635553f","schema_version":"1.0","event_id":"sha256:7a63aa6ba9b2daf8662d3bbdb22f037383372a6bf0870c15fae4eecc0635553f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:53X3API7VYK6UGU4OOHQHJQTSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chloe Yewon Chun, Ernest K. Ryu, Hyunsik Chae, Jaden Park, Mu Cai, Seungwoo Yoon, Yongin Cho, Yong Jae Lee","submitted_at":"2025-05-26T14:09:24Z","abstract_excerpt":"Recent Vision-Language Models (VLMs) have demonstrated impressive multimodal comprehension and reasoning capabilities, yet they often struggle with trivially simple visual tasks. In this work, we focus on the domain of basic 2D Euclidean geometry and systematically categorize the fundamental, indivisible visual perception skills, which we refer to as atomic visual skills. We then introduce the Atomic Visual Skills Dataset (AVSD) for evaluating VLMs on the atomic visual skills. Using AVSD, we benchmark state-of-the-art VLMs and find that they struggle with these tasks, despite being trivial for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20021","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/2505.20021/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":"2026-07-05T11:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zfyYvuZSxbbVz/C5GaaYxued975lKD24yPrGVr9AbkzNqMway5pPZmp6SuSmwh+GR1giEHOWd1FhEAYwvf54AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:35:46.058709Z"},"content_sha256":"1fda8b5622fc41101cdf1dc8094c1709644887619a27fe2d94f0d6939d786c90","schema_version":"1.0","event_id":"sha256:1fda8b5622fc41101cdf1dc8094c1709644887619a27fe2d94f0d6939d786c90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53X3API7VYK6UGU4OOHQHJQTSB/bundle.json","state_url":"https://pith.science/pith/53X3API7VYK6UGU4OOHQHJQTSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53X3API7VYK6UGU4OOHQHJQTSB/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":"2026-08-08T00:35:46Z","links":{"resolver":"https://pith.science/pith/53X3API7VYK6UGU4OOHQHJQTSB","bundle":"https://pith.science/pith/53X3API7VYK6UGU4OOHQHJQTSB/bundle.json","state":"https://pith.science/pith/53X3API7VYK6UGU4OOHQHJQTSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53X3API7VYK6UGU4OOHQHJQTSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:53X3API7VYK6UGU4OOHQHJQTSB","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":"116eb87bdc03800bcb0485832f351e9c4193210ae5d8554b25f197c3ee611345","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T14:09:24Z","title_canon_sha256":"7bb13e8b3206edb7ee62399922a54bfe580ee0416f7a4a8f31c7b09811b61c47"},"schema_version":"1.0","source":{"id":"2505.20021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20021","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20021v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20021","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"53X3API7VYK6","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"53X3API7VYK6UGU4","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"53X3API7","created_at":"2026-07-05T11:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:1fda8b5622fc41101cdf1dc8094c1709644887619a27fe2d94f0d6939d786c90","target":"graph","created_at":"2026-07-05T11:09:51Z","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/2505.20021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Vision-Language Models (VLMs) have demonstrated impressive multimodal comprehension and reasoning capabilities, yet they often struggle with trivially simple visual tasks. In this work, we focus on the domain of basic 2D Euclidean geometry and systematically categorize the fundamental, indivisible visual perception skills, which we refer to as atomic visual skills. We then introduce the Atomic Visual Skills Dataset (AVSD) for evaluating VLMs on the atomic visual skills. Using AVSD, we benchmark state-of-the-art VLMs and find that they struggle with these tasks, despite being trivial for","authors_text":"Chloe Yewon Chun, Ernest K. Ryu, Hyunsik Chae, Jaden Park, Mu Cai, Seungwoo Yoon, Yongin Cho, Yong Jae Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T14:09:24Z","title":"Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20021","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":"sha256:7a63aa6ba9b2daf8662d3bbdb22f037383372a6bf0870c15fae4eecc0635553f","target":"record","created_at":"2026-07-05T11:09:51Z","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":"116eb87bdc03800bcb0485832f351e9c4193210ae5d8554b25f197c3ee611345","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T14:09:24Z","title_canon_sha256":"7bb13e8b3206edb7ee62399922a54bfe580ee0416f7a4a8f31c7b09811b61c47"},"schema_version":"1.0","source":{"id":"2505.20021","kind":"arxiv","version":1}},"canonical_sha256":"eeefb03d1fae15ea1a9c738f03a613904d3cbd36589d3905f6f45ae97bca7fbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeefb03d1fae15ea1a9c738f03a613904d3cbd36589d3905f6f45ae97bca7fbf","first_computed_at":"2026-07-05T11:09:51.387600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:51.387600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Erld07U7e775KpQ0lFE+Fgf69/+DmAgshhnuR/sTOuZVeHZ6p3xb04HVZmNA3yc4GJ2U9JiYoZr1/0xTRbRtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:51.388090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a63aa6ba9b2daf8662d3bbdb22f037383372a6bf0870c15fae4eecc0635553f","sha256:1fda8b5622fc41101cdf1dc8094c1709644887619a27fe2d94f0d6939d786c90"],"state_sha256":"e85b1b616dbee20b2fd09a564c6fe9fe179b69de2e717811b1f34fa4df6f8917"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sH5Pl3wHOUGWI8n6CGEiyxYhzuxGcAHPIcOXRlleiaj0oNhnFqw50o2zDhltc3ysEtWOOYoaCfVQCV8nTJ0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:35:46.065071Z","bundle_sha256":"b4938aad41f7447d4b5315a21ce5e35fe1c88bf0a9c6674cae9f9d2852f95797"}}