{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4PZS2QLSM7M5RX7ZYPP6RNR3W3","short_pith_number":"pith:4PZS2QLS","schema_version":"1.0","canonical_sha256":"e3f32d417267d9d8dff9c3dfe8b63bb6ff1a1fa6e6255a4ab4c96cf7cfb59300","source":{"kind":"arxiv","id":"2510.19496","version":3},"attestation_state":"computed","paper":{"title":"CARES: Context-Aware Resolution Selector for VLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaim Baskin, Eli Schwartz, Moshe Kimhi, Nimrod Shabtay, Raja Giryes","submitted_at":"2025-10-22T11:44:31Z","abstract_excerpt":"Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens ofter to 97-99% of total tokens, resulting in high compute and latency, even when low-resolution images would suffice. We introduce \\emph{CARES}-a \\textbf{C}ontext-\\textbf{A}ware \\textbf{R}esolution \\textbf{S}elector, a lightweight preprocessing module that, given an image-query pair, predicts the \\emph{minimal} sufficient input resolution. CARES uses a compact VLM (350M) to extract features and predict when a target pretrained VLM's response co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.19496","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-22T11:44:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"956dc7d6b2ba1b2cb9027f8503ca4f562460b2b8722473e8acd99c3e17f4f17f","abstract_canon_sha256":"fcc5d040cba9527046442d733c2e40bdd296a82d10f13764962e9e63db33cc22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:10.274055Z","signature_b64":"MaxlWDSrrbKdd/EJGFeucYSl4qCCUbkfYICfpT/m+/VA8uXFTkqE2soozXGxGGrQa7z1coDVKgHOOIt90crQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3f32d417267d9d8dff9c3dfe8b63bb6ff1a1fa6e6255a4ab4c96cf7cfb59300","last_reissued_at":"2026-06-02T02:04:10.273482Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:10.273482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARES: Context-Aware Resolution Selector for VLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaim Baskin, Eli Schwartz, Moshe Kimhi, Nimrod Shabtay, Raja Giryes","submitted_at":"2025-10-22T11:44:31Z","abstract_excerpt":"Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens ofter to 97-99% of total tokens, resulting in high compute and latency, even when low-resolution images would suffice. We introduce \\emph{CARES}-a \\textbf{C}ontext-\\textbf{A}ware \\textbf{R}esolution \\textbf{S}elector, a lightweight preprocessing module that, given an image-query pair, predicts the \\emph{minimal} sufficient input resolution. CARES uses a compact VLM (350M) to extract features and predict when a target pretrained VLM's response co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.19496","kind":"arxiv","version":3},"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/2510.19496/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.19496","created_at":"2026-06-02T02:04:10.273535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.19496v3","created_at":"2026-06-02T02:04:10.273535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.19496","created_at":"2026-06-02T02:04:10.273535+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PZS2QLSM7M5","created_at":"2026-06-02T02:04:10.273535+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PZS2QLSM7M5RX7Z","created_at":"2026-06-02T02:04:10.273535+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PZS2QLS","created_at":"2026-06-02T02:04:10.273535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3","json":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3.json","graph_json":"https://pith.science/api/pith-number/4PZS2QLSM7M5RX7ZYPP6RNR3W3/graph.json","events_json":"https://pith.science/api/pith-number/4PZS2QLSM7M5RX7ZYPP6RNR3W3/events.json","paper":"https://pith.science/paper/4PZS2QLS"},"agent_actions":{"view_html":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3","download_json":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3.json","view_paper":"https://pith.science/paper/4PZS2QLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.19496&json=true","fetch_graph":"https://pith.science/api/pith-number/4PZS2QLSM7M5RX7ZYPP6RNR3W3/graph.json","fetch_events":"https://pith.science/api/pith-number/4PZS2QLSM7M5RX7ZYPP6RNR3W3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3/action/storage_attestation","attest_author":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3/action/author_attestation","sign_citation":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3/action/citation_signature","submit_replication":"https://pith.science/pith/4PZS2QLSM7M5RX7ZYPP6RNR3W3/action/replication_record"}},"created_at":"2026-06-02T02:04:10.273535+00:00","updated_at":"2026-06-02T02:04:10.273535+00:00"}