{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OSFT67S7N7ZDWKVW255OHPVINP","short_pith_number":"pith:OSFT67S7","canonical_record":{"source":{"id":"2607.15732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T08:13:01Z","cross_cats_sorted":[],"title_canon_sha256":"788485f9cc744c33ab58e08afa5b566e4002bcf855bd741adb2aae6b72b6c452","abstract_canon_sha256":"6ab192fd0c1f850811fcf4df3c73ca520f1a1c959df33b7e8cd54bd8851e4300"},"schema_version":"1.0"},"canonical_sha256":"748b3f7e5f6ff23b2ab6d77ae3bea86bcb4db8046ff5146392c5d18ad3f08807","source":{"kind":"arxiv","id":"2607.15732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15732","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15732v1","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15732","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"OSFT67S7N7ZD","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"OSFT67S7N7ZDWKVW","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"OSFT67S7","created_at":"2026-07-20T01:19:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OSFT67S7N7ZDWKVW255OHPVINP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T08:13:01Z","cross_cats_sorted":[],"title_canon_sha256":"788485f9cc744c33ab58e08afa5b566e4002bcf855bd741adb2aae6b72b6c452","abstract_canon_sha256":"6ab192fd0c1f850811fcf4df3c73ca520f1a1c959df33b7e8cd54bd8851e4300"},"schema_version":"1.0"},"canonical_sha256":"748b3f7e5f6ff23b2ab6d77ae3bea86bcb4db8046ff5146392c5d18ad3f08807","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:19:06.820022Z","signature_b64":"zqTGJ+feVrWMOvY7G6qSn/BWd4ukXB7TF/iFItZOb9FV6z01c27nYTtOfgFyUV5+CM6aNei1gxnzX2JPRGNxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"748b3f7e5f6ff23b2ab6d77ae3bea86bcb4db8046ff5146392c5d18ad3f08807","last_reissued_at":"2026-07-20T01:19:06.819109Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:19:06.819109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15732","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":"2026-07-20T01:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PaikjY7TbSs0k86+3oLdreBD9uK2fBA2KpNwH3nKd/y0ormCpSlW/MXBvsIjBV88fNALFvqv6S6mo4YXnJ9mAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:04.645327Z"},"content_sha256":"2c219c0ad6f6ce043893a33223a27f3eaa770552af184b3a70bc552dc32c365f","schema_version":"1.0","event_id":"sha256:2c219c0ad6f6ce043893a33223a27f3eaa770552af184b3a70bc552dc32c365f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OSFT67S7N7ZDWKVW255OHPVINP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IoUPD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongming Zhang, Hao Wu, Jian Xue, Ke Lu, Xiuyuan Zhu, Zijin Du","submitted_at":"2026-07-17T08:13:01Z","abstract_excerpt":"Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prompt. While this interface is simple and compatible with instruction following, it introduces a mismatch between training and evaluation: training optimizes token-level likelihood over coordinate strings, whereas grounding quality is measured by geometric overlap. We propose IoUPD, an IoU-aware privileged distillation method for coordinate-generating multimodal large language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15732","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/2607.15732/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":"2026-07-20T01:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rqo/fK26X4XO4XdVWjwCPW4IzZRG+Ln3xq6wQyYLD9RFix/deq7s8HU44DFis3PnQPJTNul3i/kMsxaEAtXwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:04.645847Z"},"content_sha256":"344c721b7252ee2425cd79d8fb8b9c9f60cf61c5c8caf0ee10a59a53420d7a7a","schema_version":"1.0","event_id":"sha256:344c721b7252ee2425cd79d8fb8b9c9f60cf61c5c8caf0ee10a59a53420d7a7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSFT67S7N7ZDWKVW255OHPVINP/bundle.json","state_url":"https://pith.science/pith/OSFT67S7N7ZDWKVW255OHPVINP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSFT67S7N7ZDWKVW255OHPVINP/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":"2026-08-04T06:06:04Z","links":{"resolver":"https://pith.science/pith/OSFT67S7N7ZDWKVW255OHPVINP","bundle":"https://pith.science/pith/OSFT67S7N7ZDWKVW255OHPVINP/bundle.json","state":"https://pith.science/pith/OSFT67S7N7ZDWKVW255OHPVINP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSFT67S7N7ZDWKVW255OHPVINP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OSFT67S7N7ZDWKVW255OHPVINP","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":"6ab192fd0c1f850811fcf4df3c73ca520f1a1c959df33b7e8cd54bd8851e4300","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T08:13:01Z","title_canon_sha256":"788485f9cc744c33ab58e08afa5b566e4002bcf855bd741adb2aae6b72b6c452"},"schema_version":"1.0","source":{"id":"2607.15732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15732","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15732v1","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15732","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"OSFT67S7N7ZD","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"OSFT67S7N7ZDWKVW","created_at":"2026-07-20T01:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"OSFT67S7","created_at":"2026-07-20T01:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:344c721b7252ee2425cd79d8fb8b9c9f60cf61c5c8caf0ee10a59a53420d7a7a","target":"graph","created_at":"2026-07-20T01:19:06Z","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/2607.15732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prompt. While this interface is simple and compatible with instruction following, it introduces a mismatch between training and evaluation: training optimizes token-level likelihood over coordinate strings, whereas grounding quality is measured by geometric overlap. We propose IoUPD, an IoU-aware privileged distillation method for coordinate-generating multimodal large language mod","authors_text":"Dongming Zhang, Hao Wu, Jian Xue, Ke Lu, Xiuyuan Zhu, Zijin Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T08:13:01Z","title":"IoUPD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15732","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":"sha256:2c219c0ad6f6ce043893a33223a27f3eaa770552af184b3a70bc552dc32c365f","target":"record","created_at":"2026-07-20T01:19:06Z","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":"6ab192fd0c1f850811fcf4df3c73ca520f1a1c959df33b7e8cd54bd8851e4300","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T08:13:01Z","title_canon_sha256":"788485f9cc744c33ab58e08afa5b566e4002bcf855bd741adb2aae6b72b6c452"},"schema_version":"1.0","source":{"id":"2607.15732","kind":"arxiv","version":1}},"canonical_sha256":"748b3f7e5f6ff23b2ab6d77ae3bea86bcb4db8046ff5146392c5d18ad3f08807","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"748b3f7e5f6ff23b2ab6d77ae3bea86bcb4db8046ff5146392c5d18ad3f08807","first_computed_at":"2026-07-20T01:19:06.819109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T01:19:06.819109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zqTGJ+feVrWMOvY7G6qSn/BWd4ukXB7TF/iFItZOb9FV6z01c27nYTtOfgFyUV5+CM6aNei1gxnzX2JPRGNxBg==","signature_status":"signed_v1","signed_at":"2026-07-20T01:19:06.820022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c219c0ad6f6ce043893a33223a27f3eaa770552af184b3a70bc552dc32c365f","sha256:344c721b7252ee2425cd79d8fb8b9c9f60cf61c5c8caf0ee10a59a53420d7a7a"],"state_sha256":"d506f514e168ac60c557e4c8ab26f8a07938e89a507bd30e2ee9e9e63b7fd6ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aHXOuuP0FZDdJ/YfT5u1dT2m1Gu3Cgir0OMZNbdLkmSqB4Go+4xMWWptufhMzKXLrd8c7dqyI2dV+wHMKZS+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:06:04.651416Z","bundle_sha256":"762c25f5d20dee2e4912648defbf249a541b4f38bd008abd77df7d6ca97c15c9"}}