{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QAVTUYJHOTN3UHO2ZUNUJHLHE4","short_pith_number":"pith:QAVTUYJH","canonical_record":{"source":{"id":"2502.17422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:54:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c7f2e11ec1418dc2b60141487ac9d66cb2564224f9b6d59b1ce61df6b7678465","abstract_canon_sha256":"fc01952cc7ee65baedb00f91cce804971110efff3f11b9130713f963915fd76f"},"schema_version":"1.0"},"canonical_sha256":"802b3a612774dbba1ddacd1b449d67273e102d8d2bbea5371981135c98954fcc","source":{"kind":"arxiv","id":"2502.17422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17422","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17422v1","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17422","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"QAVTUYJHOTN3","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"QAVTUYJHOTN3UHO2","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"QAVTUYJH","created_at":"2026-07-05T10:19:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QAVTUYJHOTN3UHO2ZUNUJHLHE4","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:54:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c7f2e11ec1418dc2b60141487ac9d66cb2564224f9b6d59b1ce61df6b7678465","abstract_canon_sha256":"fc01952cc7ee65baedb00f91cce804971110efff3f11b9130713f963915fd76f"},"schema_version":"1.0"},"canonical_sha256":"802b3a612774dbba1ddacd1b449d67273e102d8d2bbea5371981135c98954fcc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:09.956643Z","signature_b64":"8ugKNxHi/N8UQhkQjRGIF82HBrqFv2HKawVxpx4/3V77127hCaP1WIZnynltCsopkKU6s7ery2CntbdC1Tq6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"802b3a612774dbba1ddacd1b449d67273e102d8d2bbea5371981135c98954fcc","last_reissued_at":"2026-07-05T10:19:09.956148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:09.956148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17422","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":"2026-07-05T10:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4F8PpK3V9Senr3ru8dnF+h7t2+PlMZJPy7rzgboYGE958U2n1QzBXhGftMcpaVppr6vzFyV7ozX+oLeAAZlKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:43:23.347975Z"},"content_sha256":"ef1e950186badde6928d30bcbcd8363ec1a507121ff65abad0b98eafdddfc4f0","schema_version":"1.0","event_id":"sha256:ef1e950186badde6928d30bcbcd8363ec1a507121ff65abad0b98eafdddfc4f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QAVTUYJHOTN3UHO2ZUNUJHLHE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Filip Ilievski, Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara","submitted_at":"2025-02-24T18:54:40Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have experienced rapid progress in visual recognition tasks in recent years. Given their potential integration into many critical applications, it is important to understand the limitations of their visual perception. In this work, we study whether MLLMs can perceive small visual details as effectively as large ones when answering questions about images. We observe that their performance is very sensitive to the size of the visual subject of the question, and further show that this effect is in fact causal by conducting an intervention study. Next, we s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17422","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/2502.17422/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":"2026-07-05T10:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16PN4IjXHqRZodhcX4iIkZWD3W6B/ooIuTPt8J7VDQrs0VtHU6kILOAVUfX32pYwvobuDnyl5bWfhY8U66XhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:43:23.348397Z"},"content_sha256":"31f25cccbcb42c09edb7fcd37c8f9f82b3100163beb0baaa70197b565351c0be","schema_version":"1.0","event_id":"sha256:31f25cccbcb42c09edb7fcd37c8f9f82b3100163beb0baaa70197b565351c0be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4/bundle.json","state_url":"https://pith.science/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4/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":"2026-08-03T19:43:23Z","links":{"resolver":"https://pith.science/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4","bundle":"https://pith.science/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4/bundle.json","state":"https://pith.science/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QAVTUYJHOTN3UHO2ZUNUJHLHE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QAVTUYJHOTN3UHO2ZUNUJHLHE4","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":"fc01952cc7ee65baedb00f91cce804971110efff3f11b9130713f963915fd76f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:54:40Z","title_canon_sha256":"c7f2e11ec1418dc2b60141487ac9d66cb2564224f9b6d59b1ce61df6b7678465"},"schema_version":"1.0","source":{"id":"2502.17422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17422","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17422v1","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17422","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"QAVTUYJHOTN3","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"QAVTUYJHOTN3UHO2","created_at":"2026-07-05T10:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"QAVTUYJH","created_at":"2026-07-05T10:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:31f25cccbcb42c09edb7fcd37c8f9f82b3100163beb0baaa70197b565351c0be","target":"graph","created_at":"2026-07-05T10:19:09Z","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/2502.17422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have experienced rapid progress in visual recognition tasks in recent years. Given their potential integration into many critical applications, it is important to understand the limitations of their visual perception. In this work, we study whether MLLMs can perceive small visual details as effectively as large ones when answering questions about images. We observe that their performance is very sensitive to the size of the visual subject of the question, and further show that this effect is in fact causal by conducting an intervention study. Next, we s","authors_text":"Filip Ilievski, Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:54:40Z","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17422","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:ef1e950186badde6928d30bcbcd8363ec1a507121ff65abad0b98eafdddfc4f0","target":"record","created_at":"2026-07-05T10:19:09Z","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":"fc01952cc7ee65baedb00f91cce804971110efff3f11b9130713f963915fd76f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:54:40Z","title_canon_sha256":"c7f2e11ec1418dc2b60141487ac9d66cb2564224f9b6d59b1ce61df6b7678465"},"schema_version":"1.0","source":{"id":"2502.17422","kind":"arxiv","version":1}},"canonical_sha256":"802b3a612774dbba1ddacd1b449d67273e102d8d2bbea5371981135c98954fcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"802b3a612774dbba1ddacd1b449d67273e102d8d2bbea5371981135c98954fcc","first_computed_at":"2026-07-05T10:19:09.956148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:09.956148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ugKNxHi/N8UQhkQjRGIF82HBrqFv2HKawVxpx4/3V77127hCaP1WIZnynltCsopkKU6s7ery2CntbdC1Tq6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:09.956643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef1e950186badde6928d30bcbcd8363ec1a507121ff65abad0b98eafdddfc4f0","sha256:31f25cccbcb42c09edb7fcd37c8f9f82b3100163beb0baaa70197b565351c0be"],"state_sha256":"2385625de2cf02e3d4df0b9c042f8fa953bae01e050cc3ec88e5e5bf7dcecb72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bc4Rdm47KJoO5tV+WRwZK1nAjOJ7biPWhKzn030Dv2pFyASGXqXbpXi6fkAhCAQpm19C5ko3oh94Q9TswCWQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:43:23.351226Z","bundle_sha256":"c0a60563815be783d1a10ef9514616a9c119725aa5ac606968eacd59a0da8069"}}