{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:43TU6AEAKE6UNL2GNJJKWUSJJE","short_pith_number":"pith:43TU6AEA","canonical_record":{"source":{"id":"2505.14231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"3acd01f8ffd36bd0751826a15a95fafdeb831780f0681d128e1738e9b1332ac6","abstract_canon_sha256":"148edabcc6ba1726041f80f0ff2a4156db727d3c0516a40b6c5f623ad9807916"},"schema_version":"1.0"},"canonical_sha256":"e6e74f0080513d46af466a52ab5249491b7c75a3dfdea9f47d1c6801b0738aa9","source":{"kind":"arxiv","id":"2505.14231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14231","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14231v1","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14231","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"43TU6AEAKE6U","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"43TU6AEAKE6UNL2G","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"43TU6AEA","created_at":"2026-07-05T11:05:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:43TU6AEAKE6UNL2GNJJKWUSJJE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"3acd01f8ffd36bd0751826a15a95fafdeb831780f0681d128e1738e9b1332ac6","abstract_canon_sha256":"148edabcc6ba1726041f80f0ff2a4156db727d3c0516a40b6c5f623ad9807916"},"schema_version":"1.0"},"canonical_sha256":"e6e74f0080513d46af466a52ab5249491b7c75a3dfdea9f47d1c6801b0738aa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:58.052817Z","signature_b64":"Kfw8dgK6gCLRs+IwVKcKo063tIJI+flFU4RdmxUd2wG3XgSs0zgqpmP2y4GAA32w0Kfy3Pm2vT4onl8os5MgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e74f0080513d46af466a52ab5249491b7c75a3dfdea9f47d1c6801b0738aa9","last_reissued_at":"2026-07-05T11:05:58.052332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:58.052332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14231","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":"2026-07-05T11:05:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pLLFGBH742jGfKiAQBac43FMtMdmsfRO48jIVGRZ2+ncg4EoumhxCca2oHxO9QxUqjoasf67EzHoQaIV3voLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:34:15.788236Z"},"content_sha256":"e41f5aa778fe08e295123588a9b6cc0a154807ff9667ced22acece2769b5b064","schema_version":"1.0","event_id":"sha256:e41f5aa778fe08e295123588a9b6cc0a154807ff9667ced22acece2769b5b064"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:43TU6AEAKE6UNL2GNJJKWUSJJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoji Zhang, Jing Tang, Lei Sun, Mingxing Li, Sule Bai, Xiangxiang Chu, Yansong Tang, Yong Liu","submitted_at":"2025-05-20T11:40:43Z","abstract_excerpt":"Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in conjunction with multiple images, poses significant challenges, which is mainly due to the lack of advanced reasoning ability across diverse multi-modal contexts. In this work, we aim to address the more practical universal grounding task, and propose UniVG-R1, a reasoning guided multimodal large language model (MLLM) for universal visual grounding, which enhances r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14231","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/2505.14231/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":"2026-07-05T11:05:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRvrLRfByQ/KZhAM1aFy7wdOsKqSX1DVaTNJh+BWgEDkhNS6KhOxswdUSzkn6CeqOS/mBS0dWX+YkgRoYrWVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:34:15.788867Z"},"content_sha256":"9377865127fa9f64ebe3a7ddc2372d336f78487f57161aa587804de83e91b740","schema_version":"1.0","event_id":"sha256:9377865127fa9f64ebe3a7ddc2372d336f78487f57161aa587804de83e91b740"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/43TU6AEAKE6UNL2GNJJKWUSJJE/bundle.json","state_url":"https://pith.science/pith/43TU6AEAKE6UNL2GNJJKWUSJJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/43TU6AEAKE6UNL2GNJJKWUSJJE/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":"2026-08-18T23:34:15Z","links":{"resolver":"https://pith.science/pith/43TU6AEAKE6UNL2GNJJKWUSJJE","bundle":"https://pith.science/pith/43TU6AEAKE6UNL2GNJJKWUSJJE/bundle.json","state":"https://pith.science/pith/43TU6AEAKE6UNL2GNJJKWUSJJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/43TU6AEAKE6UNL2GNJJKWUSJJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:43TU6AEAKE6UNL2GNJJKWUSJJE","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":"148edabcc6ba1726041f80f0ff2a4156db727d3c0516a40b6c5f623ad9807916","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:40:43Z","title_canon_sha256":"3acd01f8ffd36bd0751826a15a95fafdeb831780f0681d128e1738e9b1332ac6"},"schema_version":"1.0","source":{"id":"2505.14231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14231","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14231v1","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14231","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"43TU6AEAKE6U","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"43TU6AEAKE6UNL2G","created_at":"2026-07-05T11:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"43TU6AEA","created_at":"2026-07-05T11:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:9377865127fa9f64ebe3a7ddc2372d336f78487f57161aa587804de83e91b740","target":"graph","created_at":"2026-07-05T11:05:58Z","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/2505.14231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in conjunction with multiple images, poses significant challenges, which is mainly due to the lack of advanced reasoning ability across diverse multi-modal contexts. In this work, we aim to address the more practical universal grounding task, and propose UniVG-R1, a reasoning guided multimodal large language model (MLLM) for universal visual grounding, which enhances r","authors_text":"Haoji Zhang, Jing Tang, Lei Sun, Mingxing Li, Sule Bai, Xiangxiang Chu, Yansong Tang, Yong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:40:43Z","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14231","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:e41f5aa778fe08e295123588a9b6cc0a154807ff9667ced22acece2769b5b064","target":"record","created_at":"2026-07-05T11:05:58Z","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":"148edabcc6ba1726041f80f0ff2a4156db727d3c0516a40b6c5f623ad9807916","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:40:43Z","title_canon_sha256":"3acd01f8ffd36bd0751826a15a95fafdeb831780f0681d128e1738e9b1332ac6"},"schema_version":"1.0","source":{"id":"2505.14231","kind":"arxiv","version":1}},"canonical_sha256":"e6e74f0080513d46af466a52ab5249491b7c75a3dfdea9f47d1c6801b0738aa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6e74f0080513d46af466a52ab5249491b7c75a3dfdea9f47d1c6801b0738aa9","first_computed_at":"2026-07-05T11:05:58.052332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:58.052332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kfw8dgK6gCLRs+IwVKcKo063tIJI+flFU4RdmxUd2wG3XgSs0zgqpmP2y4GAA32w0Kfy3Pm2vT4onl8os5MgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:58.052817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e41f5aa778fe08e295123588a9b6cc0a154807ff9667ced22acece2769b5b064","sha256:9377865127fa9f64ebe3a7ddc2372d336f78487f57161aa587804de83e91b740"],"state_sha256":"f4f38fce216236a1cfd5a244fbf8b2bd732161206488474d5e26cb10e364699f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmA5DW3q0LmTaP5BYW7zjaEjYxkFc96KgWYbU+yEP+D4whRRMQT4+A47IoWfbHq+mMoNfUeUDY6SfnBH/bHkDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:34:15.793812Z","bundle_sha256":"8eb105cfa09a2782f30a0fbcd44fdbab17ddcbc412a5e10157fa00ba0cdbad20"}}