{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JFRODULU3XULZ5VKXLFTB5CF4O","short_pith_number":"pith:JFRODULU","canonical_record":{"source":{"id":"2505.13788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T00:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"830476e38be66e8b6026e5d675c7e415e32fb7b0183300aa59c1002e28c965a5","abstract_canon_sha256":"99b10ed1cb1dd2951a94c9064e9722cc12b690cbcabe752f5f0820db8883d4f4"},"schema_version":"1.0"},"canonical_sha256":"4962e1d174dde8bcf6aabacb30f445e386a4adbf90c182d3dc44f27607fb648b","source":{"kind":"arxiv","id":"2505.13788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13788","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13788v1","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13788","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"JFRODULU3XUL","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"JFRODULU3XULZ5VK","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"JFRODULU","created_at":"2026-07-05T11:05:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JFRODULU3XULZ5VKXLFTB5CF4O","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T00:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"830476e38be66e8b6026e5d675c7e415e32fb7b0183300aa59c1002e28c965a5","abstract_canon_sha256":"99b10ed1cb1dd2951a94c9064e9722cc12b690cbcabe752f5f0820db8883d4f4"},"schema_version":"1.0"},"canonical_sha256":"4962e1d174dde8bcf6aabacb30f445e386a4adbf90c182d3dc44f27607fb648b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:51.016433Z","signature_b64":"OYAOxGI3Q/62Rwxi5Q3EeaZJLs6V3ZLYX3vyyiytVmlvTvrYw80AXJwySvwgt0T2UZids/Egv26xu9ADTDzbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4962e1d174dde8bcf6aabacb30f445e386a4adbf90c182d3dc44f27607fb648b","last_reissued_at":"2026-07-05T11:05:51.015799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:51.015799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13788","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":"2026-07-05T11:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XR5XXy74Fc2aTSS9S+W3GWAk4PSfSejBho0ntQ6s4dhliWambWsqNFXSXfPma5B7NUE0fgFpJstyI5KVzWf/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:50:30.599169Z"},"content_sha256":"8872be2f76b3838594139f718891d38ce46f4c759a08621e8b4ad68973cd6cc8","schema_version":"1.0","event_id":"sha256:8872be2f76b3838594139f718891d38ce46f4c759a08621e8b4ad68973cd6cc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JFRODULU3XULZ5VKXLFTB5CF4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsheng An, Linghan Xu, Onkar Dabeer, Qin Zhang, Xiang Xu, Yifan Xing, Yongshuo Zong, Zhihua Li, Zhuowen Tu","submitted_at":"2025-05-20T00:37:19Z","abstract_excerpt":"This work presents a simple yet effective workflow for automatically scaling instruction-following data to elicit pixel-level grounding capabilities of VLMs under complex instructions. In particular, we address five critical real-world challenges in text-instruction-based grounding: hallucinated references, multi-object scenarios, reasoning, multi-granularity, and part-level references. By leveraging knowledge distillation from a pre-trained teacher model, our approach generates high-quality instruction-response pairs linked to existing pixel-level annotations, minimizing the need for costly h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13788","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/2505.13788/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":"2026-07-05T11:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymjJjdvQ2cikndcjYkYfhOCBztxnXfz2m8bbbN7iIEyHnEPWlYuD8Kf3wpqfE9mppLHPLF9GhQEzPuTcp4VuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:50:30.599684Z"},"content_sha256":"ddba77974b6d0208c6876d1f5f8f05879083082a1b04908a83daf73bbf9a815f","schema_version":"1.0","event_id":"sha256:ddba77974b6d0208c6876d1f5f8f05879083082a1b04908a83daf73bbf9a815f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JFRODULU3XULZ5VKXLFTB5CF4O/bundle.json","state_url":"https://pith.science/pith/JFRODULU3XULZ5VKXLFTB5CF4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JFRODULU3XULZ5VKXLFTB5CF4O/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":"2026-08-11T04:50:30Z","links":{"resolver":"https://pith.science/pith/JFRODULU3XULZ5VKXLFTB5CF4O","bundle":"https://pith.science/pith/JFRODULU3XULZ5VKXLFTB5CF4O/bundle.json","state":"https://pith.science/pith/JFRODULU3XULZ5VKXLFTB5CF4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JFRODULU3XULZ5VKXLFTB5CF4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JFRODULU3XULZ5VKXLFTB5CF4O","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":"99b10ed1cb1dd2951a94c9064e9722cc12b690cbcabe752f5f0820db8883d4f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T00:37:19Z","title_canon_sha256":"830476e38be66e8b6026e5d675c7e415e32fb7b0183300aa59c1002e28c965a5"},"schema_version":"1.0","source":{"id":"2505.13788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13788","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13788v1","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13788","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"JFRODULU3XUL","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"JFRODULU3XULZ5VK","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"JFRODULU","created_at":"2026-07-05T11:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:ddba77974b6d0208c6876d1f5f8f05879083082a1b04908a83daf73bbf9a815f","target":"graph","created_at":"2026-07-05T11:05:51Z","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/2505.13788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents a simple yet effective workflow for automatically scaling instruction-following data to elicit pixel-level grounding capabilities of VLMs under complex instructions. In particular, we address five critical real-world challenges in text-instruction-based grounding: hallucinated references, multi-object scenarios, reasoning, multi-granularity, and part-level references. By leveraging knowledge distillation from a pre-trained teacher model, our approach generates high-quality instruction-response pairs linked to existing pixel-level annotations, minimizing the need for costly h","authors_text":"Dongsheng An, Linghan Xu, Onkar Dabeer, Qin Zhang, Xiang Xu, Yifan Xing, Yongshuo Zong, Zhihua Li, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T00:37:19Z","title":"Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13788","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":"sha256:8872be2f76b3838594139f718891d38ce46f4c759a08621e8b4ad68973cd6cc8","target":"record","created_at":"2026-07-05T11:05:51Z","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":"99b10ed1cb1dd2951a94c9064e9722cc12b690cbcabe752f5f0820db8883d4f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T00:37:19Z","title_canon_sha256":"830476e38be66e8b6026e5d675c7e415e32fb7b0183300aa59c1002e28c965a5"},"schema_version":"1.0","source":{"id":"2505.13788","kind":"arxiv","version":1}},"canonical_sha256":"4962e1d174dde8bcf6aabacb30f445e386a4adbf90c182d3dc44f27607fb648b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4962e1d174dde8bcf6aabacb30f445e386a4adbf90c182d3dc44f27607fb648b","first_computed_at":"2026-07-05T11:05:51.015799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:51.015799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OYAOxGI3Q/62Rwxi5Q3EeaZJLs6V3ZLYX3vyyiytVmlvTvrYw80AXJwySvwgt0T2UZids/Egv26xu9ADTDzbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:51.016433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8872be2f76b3838594139f718891d38ce46f4c759a08621e8b4ad68973cd6cc8","sha256:ddba77974b6d0208c6876d1f5f8f05879083082a1b04908a83daf73bbf9a815f"],"state_sha256":"2c9dda46be2acda712fa6634966476562d926dfa4dc99337dad53f262a3fc33a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8nIHn3vQeUJLHOx8v8kuDdyjT9y8Zy/obaZy3sl5HiW8mCY3vdH6zDVK8N0lJpefLhC/K0VCqy9Fj/FmFnoaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:50:30.604430Z","bundle_sha256":"dae3945afbcdb6d494af272f29d345180b09ddbcb00db590da35842fc9b2aca3"}}