{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PYVB4SKU2JQI35KVOJ5IWWNYWJ","short_pith_number":"pith:PYVB4SKU","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"},"canonical_sha256":"7e2a1e4954d2608df555727a8b59b8b27de9a4411e5157a74fe820dd677dad78","source":{"kind":"arxiv","id":"2403.12026","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12026","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12026v2","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12026","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"PYVB4SKU2JQI","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"PYVB4SKU2JQI35KV","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"PYVB4SKU","created_at":"2026-07-05T10:06:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PYVB4SKU2JQI35KVOJ5IWWNYWJ","target":"record","payload":{"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"},"canonical_sha256":"7e2a1e4954d2608df555727a8b59b8b27de9a4411e5157a74fe820dd677dad78","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"},"source_kind":"arxiv","source_id":"2403.12026","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6NFtqgRIYq+jptujaRRxkCUaGjj3+l2g6qaZoTxcnKEeN5jpWsCLKEIgGLfzOpwJDl/7Uf+iGZJEuBy7CYvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:01:16.255170Z"},"content_sha256":"c5a33eb34dcb023b5d219818cef2eba8cb67e5c374fbcb23c0376161f8e939ab","schema_version":"1.0","event_id":"sha256:c5a33eb34dcb023b5d219818cef2eba8cb67e5c374fbcb23c0376161f8e939ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PYVB4SKU2JQI35KVOJ5IWWNYWJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EUglNO5xoThgx2ANMxo+ETnSgKYagcKAEnMDR2ikv6BVvLQbn7tZNJXPhW4+mhmbwYtXxu/08I5O58jj0//CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:01:16.255688Z"},"content_sha256":"55b3be16a9957906f7f5714cacf81775dff8ed950f1539cd8c8091d4ca2dbeb0","schema_version":"1.0","event_id":"sha256:55b3be16a9957906f7f5714cacf81775dff8ed950f1539cd8c8091d4ca2dbeb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/bundle.json","state_url":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T01:01:16Z","links":{"resolver":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ","bundle":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/bundle.json","state":"https://pith.science/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYVB4SKU2JQI35KVOJ5IWWNYWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PYVB4SKU2JQI35KVOJ5IWWNYWJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c5c215cc7da4c65015bc38abb7e525b576096164a850d2f07c0224bfec06721a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:57:02Z","title_canon_sha256":"7ed3c51ae152346cd04ff66517b3d9e78d74e88ed5a91025367bfc19b600538b"},"schema_version":"1.0","source":{"id":"2403.12026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12026","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12026v2","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12026","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"PYVB4SKU2JQI","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"PYVB4SKU2JQI35KV","created_at":"2026-07-05T10:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"PYVB4SKU","created_at":"2026-07-05T10:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:55b3be16a9957906f7f5714cacf81775dff8ed950f1539cd8c8091d4ca2dbeb0","target":"graph","created_at":"2026-07-05T10:06:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.12026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrew Zisserman, Debidatta Dwibedi, Jonathan Tompson, Vidhi Jain, Yusuf Aytar","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:57:02Z","title":"FlexCap: Describe Anything in Images in Controllable Detail"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12026","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c5a33eb34dcb023b5d219818cef2eba8cb67e5c374fbcb23c0376161f8e939ab","target":"record","created_at":"2026-07-05T10:06:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c5c215cc7da4c65015bc38abb7e525b576096164a850d2f07c0224bfec06721a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:57:02Z","title_canon_sha256":"7ed3c51ae152346cd04ff66517b3d9e78d74e88ed5a91025367bfc19b600538b"},"schema_version":"1.0","source":{"id":"2403.12026","kind":"arxiv","version":2}},"canonical_sha256":"7e2a1e4954d2608df555727a8b59b8b27de9a4411e5157a74fe820dd677dad78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e2a1e4954d2608df555727a8b59b8b27de9a4411e5157a74fe820dd677dad78","first_computed_at":"2026-07-05T10:06:39.739553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:39.739553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x1+mblrTPa/qSFdHLTPLP6KO6Dl7xZXIIT3vomex/yYgwpN3iT2INf4S8SQbeUOmpxakUdZWyIX27LtpIRIaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:39.739993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5a33eb34dcb023b5d219818cef2eba8cb67e5c374fbcb23c0376161f8e939ab","sha256:55b3be16a9957906f7f5714cacf81775dff8ed950f1539cd8c8091d4ca2dbeb0"],"state_sha256":"6a92e0b12014b9d52e45fd3b521cd412c3e138a1e7a863ac8fb31fb3dd1f7601"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5AjkBroSMTESri7r+cwfy2AsnjAx0CfVgYMVU/6tw6Yz27wAm+kslOv1i0e9z0UmjPdeipYngrAOGjhlOkw+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:01:16.263093Z","bundle_sha256":"abd617324e2342b1b5ad8e34f7a23ca6945493691feba01ce115cdd6e2511cfe"}}