{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X4XNA6AMQNR6HP2BUFX672FQRS","short_pith_number":"pith:X4XNA6AM","schema_version":"1.0","canonical_sha256":"bf2ed0780c8363e3bf41a16fefe8b08cae72b04b7f4e0f3b4ff8adf5aeec176f","source":{"kind":"arxiv","id":"2603.19466","version":2},"attestation_state":"computed","paper":{"title":"ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Massimiliano Mancini, St\\'ephane Lathuili\\`ere, Subhankar Roy, Thomas De Min","submitted_at":"2026-03-19T20:58:03Z","abstract_excerpt":"Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar \"proactive\" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness"},"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":"2603.19466","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-19T20:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"728cc5ba978afa036ec0d4c1d81ada37580de6aae513120b192a393238102532","abstract_canon_sha256":"a44cc4c43c70727edc2da8f7e2769d01da760cb7cceb2a7f57f331e6a8b981b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:30.520716Z","signature_b64":"2RD1kmOaH7NmuseXd6Wp4FGwugvI7qFvBLfuHVdpIeIctySH+/AfUQlPHHNC2ExYIYGp7BtfP1Ol9Vy0qBfSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf2ed0780c8363e3bf41a16fefe8b08cae72b04b7f4e0f3b4ff8adf5aeec176f","last_reissued_at":"2026-06-29T01:14:30.520235Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:30.520235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Massimiliano Mancini, St\\'ephane Lathuili\\`ere, Subhankar Roy, Thomas De Min","submitted_at":"2026-03-19T20:58:03Z","abstract_excerpt":"Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar \"proactive\" behavior by requesting simple user interventions? To investigate this, we introduce ProactiveBench, a benchmark built from seven repurposed datasets that tests proactiveness across different tasks such as recognizing occluded objects, enhancing image quality, and interpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19466","kind":"arxiv","version":2},"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/2603.19466/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":"2603.19466","created_at":"2026-06-29T01:14:30.520298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.19466v2","created_at":"2026-06-29T01:14:30.520298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19466","created_at":"2026-06-29T01:14:30.520298+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4XNA6AMQNR6","created_at":"2026-06-29T01:14:30.520298+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4XNA6AMQNR6HP2B","created_at":"2026-06-29T01:14:30.520298+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4XNA6AM","created_at":"2026-06-29T01:14:30.520298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.25971","citing_title":"Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS","json":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS.json","graph_json":"https://pith.science/api/pith-number/X4XNA6AMQNR6HP2BUFX672FQRS/graph.json","events_json":"https://pith.science/api/pith-number/X4XNA6AMQNR6HP2BUFX672FQRS/events.json","paper":"https://pith.science/paper/X4XNA6AM"},"agent_actions":{"view_html":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS","download_json":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS.json","view_paper":"https://pith.science/paper/X4XNA6AM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.19466&json=true","fetch_graph":"https://pith.science/api/pith-number/X4XNA6AMQNR6HP2BUFX672FQRS/graph.json","fetch_events":"https://pith.science/api/pith-number/X4XNA6AMQNR6HP2BUFX672FQRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS/action/storage_attestation","attest_author":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS/action/author_attestation","sign_citation":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS/action/citation_signature","submit_replication":"https://pith.science/pith/X4XNA6AMQNR6HP2BUFX672FQRS/action/replication_record"}},"created_at":"2026-06-29T01:14:30.520298+00:00","updated_at":"2026-06-29T01:14:30.520298+00:00"}