{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ERZG36Q6F5HJFTQAZJLY27B2CJ","short_pith_number":"pith:ERZG36Q6","canonical_record":{"source":{"id":"2506.23785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T12:27:35Z","cross_cats_sorted":[],"title_canon_sha256":"e13daafe82529e7c4d9771336c58d5967f550c38899702ff29a1ee746b941646","abstract_canon_sha256":"fa9bf2f956c9065eb170d06e0f91c80fd6e7d720b45a94e2db2289837321b3d6"},"schema_version":"1.0"},"canonical_sha256":"24726dfa1e2f4e92ce00ca578d7c3a127e9a264523060bec60dfef75822afd42","source":{"kind":"arxiv","id":"2506.23785","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23785","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23785v1","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23785","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"ERZG36Q6F5HJ","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"ERZG36Q6F5HJFTQA","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"ERZG36Q6","created_at":"2026-07-05T11:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ERZG36Q6F5HJFTQAZJLY27B2CJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T12:27:35Z","cross_cats_sorted":[],"title_canon_sha256":"e13daafe82529e7c4d9771336c58d5967f550c38899702ff29a1ee746b941646","abstract_canon_sha256":"fa9bf2f956c9065eb170d06e0f91c80fd6e7d720b45a94e2db2289837321b3d6"},"schema_version":"1.0"},"canonical_sha256":"24726dfa1e2f4e92ce00ca578d7c3a127e9a264523060bec60dfef75822afd42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:27.964967Z","signature_b64":"GUXVn2KeI7Q7aAR5Fyht/ThIxhNwOlvACBcdAAR/BdhiMQ55eKyv9dARrUVpSirVHKNgKiAqUCsxZwQVdEpcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24726dfa1e2f4e92ce00ca578d7c3a127e9a264523060bec60dfef75822afd42","last_reissued_at":"2026-07-05T11:29:27.964491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:27.964491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23785","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mb4v1BvAH8cm5n3X4ffUNqjE4YBPAeBhDEpi4jVkZiZgdEdmlPl8L/AjIbdu0jcSLsdwkqFzJ7M87f0qjwNMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:40:14.113222Z"},"content_sha256":"05f0d176e196ae4f8b13c615e647d87958669593b0686fdcf5c2f7c10ca71556","schema_version":"1.0","event_id":"sha256:05f0d176e196ae4f8b13c615e647d87958669593b0686fdcf5c2f7c10ca71556"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ERZG36Q6F5HJFTQAZJLY27B2CJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Textualization for Image Prompted Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingzheng Wei, Jiya Saiyin, Yang Zhou, Yan Xu, Yongjian Wu","submitted_at":"2025-06-30T12:27:35Z","abstract_excerpt":"We propose VisTex-OVLM, a novel image prompted object detection method that introduces visual textualization -- a process that projects a few visual exemplars into the text feature space to enhance Object-level Vision-Language Models' (OVLMs) capability in detecting rare categories that are difficult to describe textually and nearly absent from their pre-training data, while preserving their pre-trained object-text alignment. Specifically, VisTex-OVLM leverages multi-scale textualizing blocks and a multi-stage fusion strategy to integrate visual information from visual exemplars, generating te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23785","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/2506.23785/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":"2026-07-05T11:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xz228tgaz4mAO5RMvAkPIkHvAj1Q/ynzHZ5wvZ3QpVQ1RctkbDCW3EfLZ/UG4Sy402uLOeqvIa00v43zHrSqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:40:14.113816Z"},"content_sha256":"bf0d177debd68221ca06f6168bc2fc28be27789bdcfa4d13001eda182d646295","schema_version":"1.0","event_id":"sha256:bf0d177debd68221ca06f6168bc2fc28be27789bdcfa4d13001eda182d646295"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ/bundle.json","state_url":"https://pith.science/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ/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":"2026-08-21T00:40:14Z","links":{"resolver":"https://pith.science/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ","bundle":"https://pith.science/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ/bundle.json","state":"https://pith.science/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERZG36Q6F5HJFTQAZJLY27B2CJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ERZG36Q6F5HJFTQAZJLY27B2CJ","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":"fa9bf2f956c9065eb170d06e0f91c80fd6e7d720b45a94e2db2289837321b3d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T12:27:35Z","title_canon_sha256":"e13daafe82529e7c4d9771336c58d5967f550c38899702ff29a1ee746b941646"},"schema_version":"1.0","source":{"id":"2506.23785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23785","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23785v1","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23785","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"ERZG36Q6F5HJ","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"ERZG36Q6F5HJFTQA","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"ERZG36Q6","created_at":"2026-07-05T11:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:bf0d177debd68221ca06f6168bc2fc28be27789bdcfa4d13001eda182d646295","target":"graph","created_at":"2026-07-05T11:29:27Z","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/2506.23785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose VisTex-OVLM, a novel image prompted object detection method that introduces visual textualization -- a process that projects a few visual exemplars into the text feature space to enhance Object-level Vision-Language Models' (OVLMs) capability in detecting rare categories that are difficult to describe textually and nearly absent from their pre-training data, while preserving their pre-trained object-text alignment. Specifically, VisTex-OVLM leverages multi-scale textualizing blocks and a multi-stage fusion strategy to integrate visual information from visual exemplars, generating te","authors_text":"Bingzheng Wei, Jiya Saiyin, Yang Zhou, Yan Xu, Yongjian Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T12:27:35Z","title":"Visual Textualization for Image Prompted Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23785","kind":"arxiv","version":1},"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":"sha256:05f0d176e196ae4f8b13c615e647d87958669593b0686fdcf5c2f7c10ca71556","target":"record","created_at":"2026-07-05T11:29:27Z","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":"fa9bf2f956c9065eb170d06e0f91c80fd6e7d720b45a94e2db2289837321b3d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T12:27:35Z","title_canon_sha256":"e13daafe82529e7c4d9771336c58d5967f550c38899702ff29a1ee746b941646"},"schema_version":"1.0","source":{"id":"2506.23785","kind":"arxiv","version":1}},"canonical_sha256":"24726dfa1e2f4e92ce00ca578d7c3a127e9a264523060bec60dfef75822afd42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24726dfa1e2f4e92ce00ca578d7c3a127e9a264523060bec60dfef75822afd42","first_computed_at":"2026-07-05T11:29:27.964491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:27.964491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GUXVn2KeI7Q7aAR5Fyht/ThIxhNwOlvACBcdAAR/BdhiMQ55eKyv9dARrUVpSirVHKNgKiAqUCsxZwQVdEpcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:27.964967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f0d176e196ae4f8b13c615e647d87958669593b0686fdcf5c2f7c10ca71556","sha256:bf0d177debd68221ca06f6168bc2fc28be27789bdcfa4d13001eda182d646295"],"state_sha256":"2bf963535562ce9e248af4e3ae9cc647a92edba2d06cefa912246066b47980a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q9TQzDyBkFP5vIOLo3BszhahuRAz95eriHNwVQljNLbtZDxhIu5DdwUV+v1M4qyG3Hzu9oIZvCYK6bwQK9FqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T00:40:14.117355Z","bundle_sha256":"06357737601baf45bc4a8693a21387adb97b9905c7bd979713bd400b7a394bfe"}}