{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQAFWJ5ZDGN3CU4TENO7VJVGD2","short_pith_number":"pith:EQAFWJ5Z","schema_version":"1.0","canonical_sha256":"24005b27b9199bb15393235dfaa6a61ea8fd31ccfa465d5d90bf13eba837aa35","source":{"kind":"arxiv","id":"2605.18029","version":1},"attestation_state":"computed","paper":{"title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emmanuel G. Maminta, Rowel O. Atienza","submitted_at":"2026-05-18T08:20:13Z","abstract_excerpt":"Multimodal product retrieval (MPR) underpins checkout-free retail and automated inventory systems, yet it demands fine-grained SKU discrimination that standard vision-language benchmarks fail to capture. We present the first systematic zero-shot evaluation of 190 open-source VLMs on the MPR task of the GroceryVision Challenge, isolating pre-training data, architecture, and input resolution. Our analysis yields three actionable findings. \\textbf{(1) Data quality trumps scale.} Switching from raw web-scrapes to filtered datasets delivers up to 16.6\\% accuracy gains, exceeding the benefit of doub"},"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":"2605.18029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:20:13Z","cross_cats_sorted":[],"title_canon_sha256":"311a39d4a45109c1d4dac03dfb17cbe0099e7332fb9eb7ad39a0bbd54ca42bc5","abstract_canon_sha256":"ad49ff7fc722a8405974f95548696a0c49a510dabbc7350523b0abe5f0fd757a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:12.158859Z","signature_b64":"QItsXQ0wnTrjgeswb+hyEcwoXyKLFawqv/YJyNYEEl4ny4R3oPpcSvdKCzqroDbqhHnhA7rGK3hrs4zysS99AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24005b27b9199bb15393235dfaa6a61ea8fd31ccfa465d5d90bf13eba837aa35","last_reissued_at":"2026-05-20T00:05:12.158037Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:12.158037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emmanuel G. Maminta, Rowel O. Atienza","submitted_at":"2026-05-18T08:20:13Z","abstract_excerpt":"Multimodal product retrieval (MPR) underpins checkout-free retail and automated inventory systems, yet it demands fine-grained SKU discrimination that standard vision-language benchmarks fail to capture. We present the first systematic zero-shot evaluation of 190 open-source VLMs on the MPR task of the GroceryVision Challenge, isolating pre-training data, architecture, and input resolution. Our analysis yields three actionable findings. \\textbf{(1) Data quality trumps scale.} Switching from raw web-scrapes to filtered datasets delivers up to 16.6\\% accuracy gains, exceeding the benefit of doub"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18029","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/2605.18029/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.510380Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5638b2147b605a70c5b081c6267553e5a72bebb6113e2df8e22d5a9d1628d74b"},"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":"2605.18029","created_at":"2026-05-20T00:05:12.158142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18029v1","created_at":"2026-05-20T00:05:12.158142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18029","created_at":"2026-05-20T00:05:12.158142+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQAFWJ5ZDGN3","created_at":"2026-05-20T00:05:12.158142+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQAFWJ5ZDGN3CU4T","created_at":"2026-05-20T00:05:12.158142+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQAFWJ5Z","created_at":"2026-05-20T00:05:12.158142+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/EQAFWJ5ZDGN3CU4TENO7VJVGD2","json":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2.json","graph_json":"https://pith.science/api/pith-number/EQAFWJ5ZDGN3CU4TENO7VJVGD2/graph.json","events_json":"https://pith.science/api/pith-number/EQAFWJ5ZDGN3CU4TENO7VJVGD2/events.json","paper":"https://pith.science/paper/EQAFWJ5Z"},"agent_actions":{"view_html":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2","download_json":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2.json","view_paper":"https://pith.science/paper/EQAFWJ5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18029&json=true","fetch_graph":"https://pith.science/api/pith-number/EQAFWJ5ZDGN3CU4TENO7VJVGD2/graph.json","fetch_events":"https://pith.science/api/pith-number/EQAFWJ5ZDGN3CU4TENO7VJVGD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2/action/storage_attestation","attest_author":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2/action/author_attestation","sign_citation":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2/action/citation_signature","submit_replication":"https://pith.science/pith/EQAFWJ5ZDGN3CU4TENO7VJVGD2/action/replication_record"}},"created_at":"2026-05-20T00:05:12.158142+00:00","updated_at":"2026-05-20T00:05:12.158142+00:00"}