{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7CZNMQK7ZXVHMHDBS53LMW63F3","short_pith_number":"pith:7CZNMQK7","canonical_record":{"source":{"id":"2607.08541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T14:35:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dedf99bb1624a5894e8f52f84cbc6a457a2c7a6d01217a60288d0b99d33c5425","abstract_canon_sha256":"81d4cf6220cdce4ca9d9908378a12c079a0a3973e048ac31f57c23a52bcb8abc"},"schema_version":"1.0"},"canonical_sha256":"f8b2d6415fcdea761c619776b65bdb2ec72b54355baf1ac56e5026e9977140a0","source":{"kind":"arxiv","id":"2607.08541","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08541","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08541v1","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08541","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"7CZNMQK7ZXVH","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"7CZNMQK7ZXVHMHDB","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"7CZNMQK7","created_at":"2026-07-10T01:19:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7CZNMQK7ZXVHMHDBS53LMW63F3","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T14:35:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dedf99bb1624a5894e8f52f84cbc6a457a2c7a6d01217a60288d0b99d33c5425","abstract_canon_sha256":"81d4cf6220cdce4ca9d9908378a12c079a0a3973e048ac31f57c23a52bcb8abc"},"schema_version":"1.0"},"canonical_sha256":"f8b2d6415fcdea761c619776b65bdb2ec72b54355baf1ac56e5026e9977140a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:53.194537Z","signature_b64":"WlBZamgsIHd4eDtGfRr2NR2tmowbqfEFSzS8zo3nuwCWCQsEXypnrfnvwgICY62XL1E3zNlu/cNc4w+C1aAECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b2d6415fcdea761c619776b65bdb2ec72b54355baf1ac56e5026e9977140a0","last_reissued_at":"2026-07-10T01:19:53.194136Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:53.194136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08541","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":"2026-07-10T01:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3yqcCKg4bEQ6fOKqTo+aTmqTqRncDuNXgseOeYPvpmT8jbFJR3MnTqrwiEwh84d/hXTNDAwox9aY8rMwYpvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:51:51.500799Z"},"content_sha256":"35c0cc74c0ef0cbe903e21e25b02b787a1ccf8794152076d5035bc9fcceb50db","schema_version":"1.0","event_id":"sha256:35c0cc74c0ef0cbe903e21e25b02b787a1ccf8794152076d5035bc9fcceb50db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7CZNMQK7ZXVHMHDBS53LMW63F3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"ZhiXin Sun","submitted_at":"2026-07-09T14:35:37Z","abstract_excerpt":"Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often rely on text prompts, limited visual examples, or expensive feature matching procedures, making them difficult to scale to large and continuously expanding object repositories. In this work, we propose VocaDet, a sample-driven open-vocabulary object detection and segmentation framework that learns object concepts directly from user-provided positive and negative sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08541","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/2607.08541/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":"2026-07-10T01:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqQhWfyjpqO2EcdjaHdltZ9Z7rE58lxn2F2MOCrALWwWaCdzg4VxTid6hxRVDCDFMHMDCaV539hA057pw9MpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:51:51.501743Z"},"content_sha256":"a36fe5af42cf78e0d8dff134ef87fa58e74528abaea9e636c677cebe0dccd258","schema_version":"1.0","event_id":"sha256:a36fe5af42cf78e0d8dff134ef87fa58e74528abaea9e636c677cebe0dccd258"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CZNMQK7ZXVHMHDBS53LMW63F3/bundle.json","state_url":"https://pith.science/pith/7CZNMQK7ZXVHMHDBS53LMW63F3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CZNMQK7ZXVHMHDBS53LMW63F3/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":"2026-08-02T13:51:51Z","links":{"resolver":"https://pith.science/pith/7CZNMQK7ZXVHMHDBS53LMW63F3","bundle":"https://pith.science/pith/7CZNMQK7ZXVHMHDBS53LMW63F3/bundle.json","state":"https://pith.science/pith/7CZNMQK7ZXVHMHDBS53LMW63F3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CZNMQK7ZXVHMHDBS53LMW63F3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7CZNMQK7ZXVHMHDBS53LMW63F3","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":"81d4cf6220cdce4ca9d9908378a12c079a0a3973e048ac31f57c23a52bcb8abc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T14:35:37Z","title_canon_sha256":"dedf99bb1624a5894e8f52f84cbc6a457a2c7a6d01217a60288d0b99d33c5425"},"schema_version":"1.0","source":{"id":"2607.08541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08541","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08541v1","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08541","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"7CZNMQK7ZXVH","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"7CZNMQK7ZXVHMHDB","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"7CZNMQK7","created_at":"2026-07-10T01:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:a36fe5af42cf78e0d8dff134ef87fa58e74528abaea9e636c677cebe0dccd258","target":"graph","created_at":"2026-07-10T01:19:53Z","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/2607.08541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often rely on text prompts, limited visual examples, or expensive feature matching procedures, making them difficult to scale to large and continuously expanding object repositories. In this work, we propose VocaDet, a sample-driven open-vocabulary object detection and segmentation framework that learns object concepts directly from user-provided positive and negative sample","authors_text":"ZhiXin Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T14:35:37Z","title":"VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08541","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":"sha256:35c0cc74c0ef0cbe903e21e25b02b787a1ccf8794152076d5035bc9fcceb50db","target":"record","created_at":"2026-07-10T01:19:53Z","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":"81d4cf6220cdce4ca9d9908378a12c079a0a3973e048ac31f57c23a52bcb8abc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T14:35:37Z","title_canon_sha256":"dedf99bb1624a5894e8f52f84cbc6a457a2c7a6d01217a60288d0b99d33c5425"},"schema_version":"1.0","source":{"id":"2607.08541","kind":"arxiv","version":1}},"canonical_sha256":"f8b2d6415fcdea761c619776b65bdb2ec72b54355baf1ac56e5026e9977140a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8b2d6415fcdea761c619776b65bdb2ec72b54355baf1ac56e5026e9977140a0","first_computed_at":"2026-07-10T01:19:53.194136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:53.194136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WlBZamgsIHd4eDtGfRr2NR2tmowbqfEFSzS8zo3nuwCWCQsEXypnrfnvwgICY62XL1E3zNlu/cNc4w+C1aAECQ==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:53.194537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35c0cc74c0ef0cbe903e21e25b02b787a1ccf8794152076d5035bc9fcceb50db","sha256:a36fe5af42cf78e0d8dff134ef87fa58e74528abaea9e636c677cebe0dccd258"],"state_sha256":"d70f6d67044103d0bcb7f2ec763b43df909b14c2a33c1afa737f6d7fa3aadc5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/4pEMLUk5B3qMsF2MNFxu4B5VHfVpr/I2TcxlUM+KqYGE3F149EpKRR5ItZRWoP3seRd4IzbJtSMHDVOb1pBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T13:51:51.516378Z","bundle_sha256":"404cc8f9e69de17d0a430e471c343857616fabaeb92d3662c5a757667c898cc2"}}