{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2KNSO4YSG62ZLW2D4DU2JAZLZK","short_pith_number":"pith:2KNSO4YS","canonical_record":{"source":{"id":"2606.18846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T09:25:59Z","cross_cats_sorted":[],"title_canon_sha256":"84a0a6e0cf5051356a0a25a41a690628f816627c1f9be5d1fb9d425b86ce72d3","abstract_canon_sha256":"8b059a6824a2241a3c444c06f17caefd1224c2ee76eede3ddc0b688aa2316527"},"schema_version":"1.0"},"canonical_sha256":"d29b27731237b595db43e0e9a4832bca81a472173d137565587049194e4cc713","source":{"kind":"arxiv","id":"2606.18846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18846","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18846v1","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18846","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"2KNSO4YSG62Z","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"2KNSO4YSG62ZLW2D","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"2KNSO4YS","created_at":"2026-06-19T16:11:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2KNSO4YSG62ZLW2D4DU2JAZLZK","target":"record","payload":{"canonical_record":{"source":{"id":"2606.18846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T09:25:59Z","cross_cats_sorted":[],"title_canon_sha256":"84a0a6e0cf5051356a0a25a41a690628f816627c1f9be5d1fb9d425b86ce72d3","abstract_canon_sha256":"8b059a6824a2241a3c444c06f17caefd1224c2ee76eede3ddc0b688aa2316527"},"schema_version":"1.0"},"canonical_sha256":"d29b27731237b595db43e0e9a4832bca81a472173d137565587049194e4cc713","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:49.252521Z","signature_b64":"d2mRB7F1PWxfG5QY0Z+X007XUMTAiNbrD7SoCgxT1HrFFEm6iwfSXq+axI2C/W/v6Qjf1kkB/MKtSQHRjlPKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d29b27731237b595db43e0e9a4832bca81a472173d137565587049194e4cc713","last_reissued_at":"2026-06-19T16:11:49.252163Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:49.252163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.18846","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":"2026-06-19T16:11:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2qDpLXSQxxhIfGODEMHPnq44uQENzrI073nsDIZ1mcO4qXFUqUCnDbA8zBPh2I7HyE6j3QkrNMjviAhVvesBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:06:08.496083Z"},"content_sha256":"bad02488c232fc95d495caffda5a0ffbeec56a5c26fe10c88a15005eed3ad179","schema_version":"1.0","event_id":"sha256:bad02488c232fc95d495caffda5a0ffbeec56a5c26fe10c88a15005eed3ad179"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2KNSO4YSG62ZLW2D4DU2JAZLZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Bounding Boxes to Visual Reasoning: An On-Policy Data Annotation Tool for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Like Zhang, Pan Wang, Qianli Xing, Qingzu He, Qi Wang, Runliang Niu, Shiqi Wang, Xiyu Hu","submitted_at":"2026-06-17T09:25:59Z","abstract_excerpt":"Vision-language models (VLMs) are rapidly advancing toward sophisticated grounded structured visual reasoning. Training models for such advanced capabilities demands a new genre of data that seamlessly unifies spatial coordinates, open-vocabulary descriptions, structured attributes, and topological relationships into a singular representation. However, existing data annotation tools fundamentally fail to meet these intricate demands, suffering from three systematic bottlenecks: limited expressiveness, severe annotation-training decoupling, and poor data reusability. To bridge this infrastructu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18846","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/2606.18846/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":"2026-06-19T16:11:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKIQ7ohJF8ofqSI3R4xwDLfJbFme6ocSWEvdw+8IvlnoM5xDGp3YClrIiNhBMAudPF7QZ9Ibrr6i4cFgCgBVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:06:08.496477Z"},"content_sha256":"e98aeb9a2a0e36985685e6d2ec6036942a478329ba90d76bb222ffc3fe11db5e","schema_version":"1.0","event_id":"sha256:e98aeb9a2a0e36985685e6d2ec6036942a478329ba90d76bb222ffc3fe11db5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK/bundle.json","state_url":"https://pith.science/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK/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":"2026-07-04T11:06:08Z","links":{"resolver":"https://pith.science/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK","bundle":"https://pith.science/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK/bundle.json","state":"https://pith.science/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KNSO4YSG62ZLW2D4DU2JAZLZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2KNSO4YSG62ZLW2D4DU2JAZLZK","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":"8b059a6824a2241a3c444c06f17caefd1224c2ee76eede3ddc0b688aa2316527","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T09:25:59Z","title_canon_sha256":"84a0a6e0cf5051356a0a25a41a690628f816627c1f9be5d1fb9d425b86ce72d3"},"schema_version":"1.0","source":{"id":"2606.18846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18846","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18846v1","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18846","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"2KNSO4YSG62Z","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"2KNSO4YSG62ZLW2D","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"2KNSO4YS","created_at":"2026-06-19T16:11:49Z"}],"graph_snapshots":[{"event_id":"sha256:e98aeb9a2a0e36985685e6d2ec6036942a478329ba90d76bb222ffc3fe11db5e","target":"graph","created_at":"2026-06-19T16:11:49Z","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/2606.18846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are rapidly advancing toward sophisticated grounded structured visual reasoning. Training models for such advanced capabilities demands a new genre of data that seamlessly unifies spatial coordinates, open-vocabulary descriptions, structured attributes, and topological relationships into a singular representation. However, existing data annotation tools fundamentally fail to meet these intricate demands, suffering from three systematic bottlenecks: limited expressiveness, severe annotation-training decoupling, and poor data reusability. To bridge this infrastructu","authors_text":"Like Zhang, Pan Wang, Qianli Xing, Qingzu He, Qi Wang, Runliang Niu, Shiqi Wang, Xiyu Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T09:25:59Z","title":"From Bounding Boxes to Visual Reasoning: An On-Policy Data Annotation Tool for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18846","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:bad02488c232fc95d495caffda5a0ffbeec56a5c26fe10c88a15005eed3ad179","target":"record","created_at":"2026-06-19T16:11:49Z","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":"8b059a6824a2241a3c444c06f17caefd1224c2ee76eede3ddc0b688aa2316527","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T09:25:59Z","title_canon_sha256":"84a0a6e0cf5051356a0a25a41a690628f816627c1f9be5d1fb9d425b86ce72d3"},"schema_version":"1.0","source":{"id":"2606.18846","kind":"arxiv","version":1}},"canonical_sha256":"d29b27731237b595db43e0e9a4832bca81a472173d137565587049194e4cc713","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d29b27731237b595db43e0e9a4832bca81a472173d137565587049194e4cc713","first_computed_at":"2026-06-19T16:11:49.252163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:49.252163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d2mRB7F1PWxfG5QY0Z+X007XUMTAiNbrD7SoCgxT1HrFFEm6iwfSXq+axI2C/W/v6Qjf1kkB/MKtSQHRjlPKCw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:49.252521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bad02488c232fc95d495caffda5a0ffbeec56a5c26fe10c88a15005eed3ad179","sha256:e98aeb9a2a0e36985685e6d2ec6036942a478329ba90d76bb222ffc3fe11db5e"],"state_sha256":"129025fcf093ca26c786b79364c88a3fb487595e2c1813431c2ee8e64e24a1ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+T3qMC2jZQ84PPqTp/2sQ5f/81GENHyRU7MWT4BYN/V1YfOKSHOB+4NJf8xcaEsD4qrCb4Y9XAmPSdHkzIOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T11:06:08.498437Z","bundle_sha256":"b5a91381f8c0b3739e58c03064607afc86f13464f53484b26fe300af92df3ccb"}}