{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PYVB4SKU2JQI35KVOJ5IWWNYWJ","short_pith_number":"pith:PYVB4SKU","schema_version":"1.0","canonical_sha256":"7e2a1e4954d2608df555727a8b59b8b27de9a4411e5157a74fe820dd677dad78","source":{"kind":"arxiv","id":"2403.12026","version":2},"attestation_state":"computed","paper":{"title":"FlexCap: Describe Anything in Images in Controllable Detail","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Debidatta Dwibedi, Jonathan Tompson, Vidhi Jain, Yusuf Aytar","submitted_at":"2024-03-18T17:57:02Z","abstract_excerpt":"We introduce FlexCap, a vision-language model that generates region-specific descriptions of varying lengths. FlexCap is trained to produce length-conditioned captions for input boxes, enabling control over information density, with descriptions ranging from concise object labels to detailed captions. To achieve this, we create large-scale training datasets of image region descriptions with varying lengths from captioned web images. We demonstrate FlexCap's effectiveness in several applications: first, it achieves strong performance in dense captioning tasks on the Visual Genome dataset. Secon"},"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":"2403.12026","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:57:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7ed3c51ae152346cd04ff66517b3d9e78d74e88ed5a91025367bfc19b600538b","abstract_canon_sha256":"c5c215cc7da4c65015bc38abb7e525b576096164a850d2f07c0224bfec06721a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:39.739993Z","signature_b64":"x1+mblrTPa/qSFdHLTPLP6KO6Dl7xZXIIT3vomex/yYgwpN3iT2INf4S8SQbeUOmpxakUdZWyIX27LtpIRIaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e2a1e4954d2608df555727a8b59b8b27de9a4411e5157a74fe820dd677dad78","last_reissued_at":"2026-07-05T10:06:39.739553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:39.739553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlexCap: Describe Anything in Images in Controllable Detail","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Debidatta Dwibedi, Jonathan Tompson, Vidhi Jain, Yusuf Aytar","submitted_at":"2024-03-18T17:57:02Z","abstract_excerpt":"We introduce FlexCap, a vision-language model that generates region-specific descriptions of varying lengths. FlexCap is trained to produce length-conditioned captions for input boxes, enabling control over information density, with descriptions ranging from concise object labels to detailed captions. To achieve this, we create large-scale training datasets of image region descriptions with varying lengths from captioned web images. We demonstrate FlexCap's effectiveness in several applications: first, it achieves strong performance in dense captioning tasks on the Visual Genome dataset. Secon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12026","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/2403.12026/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":"2403.12026","created_at":"2026-07-05T10:06:39.739609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12026v2","created_at":"2026-07-05T10:06:39.739609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12026","created_at":"2026-07-05T10:06:39.739609+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYVB4SKU2JQI","created_at":"2026-07-05T10:06:39.739609+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYVB4SKU2JQI35KV","created_at":"2026-07-05T10:06:39.739609+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYVB4SKU","created_at":"2026-07-05T10:06:39.739609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19106","citing_title":"Detailed Object Description with Controllable Dimensions","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ","json":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ.json","graph_json":"https://pith.science/api/pith-number/PYVB4SKU2JQI35KVOJ5IWWNYWJ/graph.json","events_json":"https://pith.science/api/pith-number/PYVB4SKU2JQI35KVOJ5IWWNYWJ/events.json","paper":"https://pith.science/paper/PYVB4SKU"},"agent_actions":{"view_html":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ","download_json":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ.json","view_paper":"https://pith.science/paper/PYVB4SKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12026&json=true","fetch_graph":"https://pith.science/api/pith-number/PYVB4SKU2JQI35KVOJ5IWWNYWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PYVB4SKU2JQI35KVOJ5IWWNYWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/action/storage_attestation","attest_author":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/action/author_attestation","sign_citation":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/action/citation_signature","submit_replication":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/action/replication_record"}},"created_at":"2026-07-05T10:06:39.739609+00:00","updated_at":"2026-07-05T10:06:39.739609+00:00"}