{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6CCEHK5Z3ICBVROL6LQNGZ2ZCR","short_pith_number":"pith:6CCEHK5Z","schema_version":"1.0","canonical_sha256":"f08443abb9da041ac5cbf2e0d3675914450a0445e201782e239e3d8f99a38131","source":{"kind":"arxiv","id":"2606.04880","version":1},"attestation_state":"computed","paper":{"title":"MAOAM: Unified Object and Material Selection with Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iliyan Georgiev, Jaden Park, Jason Kuen, Kangning Liu, Krishna Kumar Singh, Michael Fischer, Valentin Deschaintre, Yong Jae Lee","submitted_at":"2026-06-02T17:59:57Z","abstract_excerpt":"Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existing vision-language-model (VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In "},"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":"2606.04880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"f79891fab5652afe431ed2d3a3012576bacd9d8615c8d02e8dede781a67403f3","abstract_canon_sha256":"fcdbf06829100825e75e6e822a0489551d5af104605f0f30fa0eb9fdb2c078b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:53.161569Z","signature_b64":"BFgJSxPyGNrttaI8yV67/Vn28QxQ9j7xIIVrDzS5yQwJQKJ8C6GRJAKQzc4U7YyYchbwvd+kEaT3QO9/OttKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08443abb9da041ac5cbf2e0d3675914450a0445e201782e239e3d8f99a38131","last_reissued_at":"2026-06-04T01:09:53.160716Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:53.160716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAOAM: Unified Object and Material Selection with Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iliyan Georgiev, Jaden Park, Jason Kuen, Kangning Liu, Krishna Kumar Singh, Michael Fischer, Valentin Deschaintre, Yong Jae Lee","submitted_at":"2026-06-02T17:59:57Z","abstract_excerpt":"Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existing vision-language-model (VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04880","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/2606.04880/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":"2606.04880","created_at":"2026-06-04T01:09:53.160855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04880v1","created_at":"2026-06-04T01:09:53.160855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04880","created_at":"2026-06-04T01:09:53.160855+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CCEHK5Z3ICB","created_at":"2026-06-04T01:09:53.160855+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CCEHK5Z3ICBVROL","created_at":"2026-06-04T01:09:53.160855+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CCEHK5Z","created_at":"2026-06-04T01:09:53.160855+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/6CCEHK5Z3ICBVROL6LQNGZ2ZCR","json":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR.json","graph_json":"https://pith.science/api/pith-number/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/graph.json","events_json":"https://pith.science/api/pith-number/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/events.json","paper":"https://pith.science/paper/6CCEHK5Z"},"agent_actions":{"view_html":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR","download_json":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR.json","view_paper":"https://pith.science/paper/6CCEHK5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04880&json=true","fetch_graph":"https://pith.science/api/pith-number/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/graph.json","fetch_events":"https://pith.science/api/pith-number/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/action/storage_attestation","attest_author":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/action/author_attestation","sign_citation":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/action/citation_signature","submit_replication":"https://pith.science/pith/6CCEHK5Z3ICBVROL6LQNGZ2ZCR/action/replication_record"}},"created_at":"2026-06-04T01:09:53.160855+00:00","updated_at":"2026-06-04T01:09:53.160855+00:00"}