{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ENTLOY6KLJM3I3M3PLSMDVWS4R","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":"f1f963d83fccd31829d5005fc44145a8d6f8cca2e108763843cd8c9bb1625089","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T08:32:35Z","title_canon_sha256":"071053723a13e82528242eb34d577369288e2054c640e6b21d94af60dd3141cd"},"schema_version":"1.0","source":{"id":"2606.29267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29267","created_at":"2026-06-30T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29267v1","created_at":"2026-06-30T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29267","created_at":"2026-06-30T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"ENTLOY6KLJM3","created_at":"2026-06-30T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"ENTLOY6KLJM3I3M3","created_at":"2026-06-30T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"ENTLOY6K","created_at":"2026-06-30T01:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:69b26de2fcf894a7547af9567d10f63cd4b7f8c17cb243a792b6ca90a2e63b17","target":"graph","created_at":"2026-06-30T01:17:59Z","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/2606.29267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding aims to associate free-form textual queries with specific regions in an image. While recent Multimodal Large Language Models (MLLMs) have demonstrated promising capabilities in this domain, they primarily excel at object-level grounding and often struggle with part-level grounding-an essential requirement for fine-grained tasks such as robotic manipulation. In this work, we introduce a general approach that equips any open-source MLLMs with accurate 2D part-level point grounding, offering a more direct alternative to conventional grounding representations. Our method leverages","authors_text":"Cheng-Hao Kuo, Fu-En Wang, Jin-Cheng Jhang, Lu Xia, Min Sun, Nan Qiao, Xin Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T08:32:35Z","title":"Enhancing Part-Level Point Grounding for Any Open-Source MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29267","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":"sha256:661d48557a6e37d99f2d73351895b8e0f2fcd75e1fc0cdf7e146d16fb6a4267d","target":"record","created_at":"2026-06-30T01:17:59Z","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":"f1f963d83fccd31829d5005fc44145a8d6f8cca2e108763843cd8c9bb1625089","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T08:32:35Z","title_canon_sha256":"071053723a13e82528242eb34d577369288e2054c640e6b21d94af60dd3141cd"},"schema_version":"1.0","source":{"id":"2606.29267","kind":"arxiv","version":1}},"canonical_sha256":"2366b763ca5a59b46d9b7ae4c1d6d2e46a278a84abcc15640fe3b764558e12e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2366b763ca5a59b46d9b7ae4c1d6d2e46a278a84abcc15640fe3b764558e12e0","first_computed_at":"2026-06-30T01:17:59.676626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:59.676626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Et7WVGMf9II/pFSVWS6VQIcVzIo1HAKovZkmKXQS9qcxH9aUDTsLNIZyAZcUA0q6KYTrWstr8az+Rg+0pAd4CQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:59.677146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:661d48557a6e37d99f2d73351895b8e0f2fcd75e1fc0cdf7e146d16fb6a4267d","sha256:69b26de2fcf894a7547af9567d10f63cd4b7f8c17cb243a792b6ca90a2e63b17"],"state_sha256":"da85643f20b94b22e4c708b51c19c323e966d88742dc7181f931bd645a85302a"}