{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IM64NQXJNLMRTULDU5XTYLYNKP","short_pith_number":"pith:IM64NQXJ","canonical_record":{"source":{"id":"2507.18300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T11:05:24Z","cross_cats_sorted":[],"title_canon_sha256":"32e4da814c5bd7970ef0e029b83064f779040f6246ca1f31be6b3a1930ab095d","abstract_canon_sha256":"aea404da0feff786ea5de9197b412b059851b2bf532280d306db738063638a8e"},"schema_version":"1.0"},"canonical_sha256":"433dc6c2e96ad919d163a76f3c2f0d53e1cc52226fcae93b2d7523af86a90b3a","source":{"kind":"arxiv","id":"2507.18300","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18300","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18300v1","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18300","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"IM64NQXJNLMR","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"IM64NQXJNLMRTULD","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"IM64NQXJ","created_at":"2026-07-05T11:42:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IM64NQXJNLMRTULDU5XTYLYNKP","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T11:05:24Z","cross_cats_sorted":[],"title_canon_sha256":"32e4da814c5bd7970ef0e029b83064f779040f6246ca1f31be6b3a1930ab095d","abstract_canon_sha256":"aea404da0feff786ea5de9197b412b059851b2bf532280d306db738063638a8e"},"schema_version":"1.0"},"canonical_sha256":"433dc6c2e96ad919d163a76f3c2f0d53e1cc52226fcae93b2d7523af86a90b3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:45.605501Z","signature_b64":"DOcF4L8FeyBXOq2OTecmk1KAUrH358WcynHOocD6cT7WGEx5AJB7elc/Eyp4lHmVSePBw3bpNyj9BDV07SDIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433dc6c2e96ad919d163a76f3c2f0d53e1cc52226fcae93b2d7523af86a90b3a","last_reissued_at":"2026-07-05T11:42:45.605053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:45.605053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18300","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":"2026-07-05T11:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85HXcqVaDJBn4Kg+3iwj9LNZwJov0U7M7KO/l6XigH75tqSjsxYlKnuGolQAzFpqdiz2OKMe9NdRuWFIvJW5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:08:02.418974Z"},"content_sha256":"6a39c11b17b0fa33e0e7cfe96e6b13e98b06cc52d29ae78f330d39b39c84ccec","schema_version":"1.0","event_id":"sha256:6a39c11b17b0fa33e0e7cfe96e6b13e98b06cc52d29ae78f330d39b39c84ccec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IM64NQXJNLMRTULDU5XTYLYNKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LMM-Det: Make Large Multimodal Models Excel in Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Xie, Dawei Leng, Ji Ao, Jincheng Li, Yuhui Yin","submitted_at":"2025-07-24T11:05:24Z","abstract_excerpt":"Large multimodal models (LMMs) have garnered wide-spread attention and interest within the artificial intelligence research and industrial communities, owing to their remarkable capability in multimodal understanding, reasoning, and in-context learning, among others. While LMMs have demonstrated promising results in tackling multimodal tasks like image captioning, visual question answering, and visual grounding, the object detection capabilities of LMMs exhibit a significant gap compared to specialist detectors. To bridge the gap, we depart from the conventional methods of integrating heavy de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18300","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/2507.18300/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":"2026-07-05T11:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vuG2xHU3qYoM+E5TNmKE+O25zu27UT45qRQw7iTsyRD4paAxT/5TyKrm00nbWG4/AbrGo6CPTGmZ6ZQuXGn7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:08:02.419487Z"},"content_sha256":"7ca84b7ea6f26b5d02bf6eb3460c44db7b0a73538b5246275323d0c29626b9aa","schema_version":"1.0","event_id":"sha256:7ca84b7ea6f26b5d02bf6eb3460c44db7b0a73538b5246275323d0c29626b9aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IM64NQXJNLMRTULDU5XTYLYNKP/bundle.json","state_url":"https://pith.science/pith/IM64NQXJNLMRTULDU5XTYLYNKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IM64NQXJNLMRTULDU5XTYLYNKP/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":"2026-08-16T07:08:02Z","links":{"resolver":"https://pith.science/pith/IM64NQXJNLMRTULDU5XTYLYNKP","bundle":"https://pith.science/pith/IM64NQXJNLMRTULDU5XTYLYNKP/bundle.json","state":"https://pith.science/pith/IM64NQXJNLMRTULDU5XTYLYNKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IM64NQXJNLMRTULDU5XTYLYNKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IM64NQXJNLMRTULDU5XTYLYNKP","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":"aea404da0feff786ea5de9197b412b059851b2bf532280d306db738063638a8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T11:05:24Z","title_canon_sha256":"32e4da814c5bd7970ef0e029b83064f779040f6246ca1f31be6b3a1930ab095d"},"schema_version":"1.0","source":{"id":"2507.18300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18300","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18300v1","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18300","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"IM64NQXJNLMR","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"IM64NQXJNLMRTULD","created_at":"2026-07-05T11:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"IM64NQXJ","created_at":"2026-07-05T11:42:45Z"}],"graph_snapshots":[{"event_id":"sha256:7ca84b7ea6f26b5d02bf6eb3460c44db7b0a73538b5246275323d0c29626b9aa","target":"graph","created_at":"2026-07-05T11:42:45Z","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/2507.18300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models (LMMs) have garnered wide-spread attention and interest within the artificial intelligence research and industrial communities, owing to their remarkable capability in multimodal understanding, reasoning, and in-context learning, among others. While LMMs have demonstrated promising results in tackling multimodal tasks like image captioning, visual question answering, and visual grounding, the object detection capabilities of LMMs exhibit a significant gap compared to specialist detectors. To bridge the gap, we depart from the conventional methods of integrating heavy de","authors_text":"Chunyu Xie, Dawei Leng, Ji Ao, Jincheng Li, Yuhui Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T11:05:24Z","title":"LMM-Det: Make Large Multimodal Models Excel in Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18300","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":"sha256:6a39c11b17b0fa33e0e7cfe96e6b13e98b06cc52d29ae78f330d39b39c84ccec","target":"record","created_at":"2026-07-05T11:42:45Z","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":"aea404da0feff786ea5de9197b412b059851b2bf532280d306db738063638a8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T11:05:24Z","title_canon_sha256":"32e4da814c5bd7970ef0e029b83064f779040f6246ca1f31be6b3a1930ab095d"},"schema_version":"1.0","source":{"id":"2507.18300","kind":"arxiv","version":1}},"canonical_sha256":"433dc6c2e96ad919d163a76f3c2f0d53e1cc52226fcae93b2d7523af86a90b3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"433dc6c2e96ad919d163a76f3c2f0d53e1cc52226fcae93b2d7523af86a90b3a","first_computed_at":"2026-07-05T11:42:45.605053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:45.605053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOcF4L8FeyBXOq2OTecmk1KAUrH358WcynHOocD6cT7WGEx5AJB7elc/Eyp4lHmVSePBw3bpNyj9BDV07SDIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:45.605501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a39c11b17b0fa33e0e7cfe96e6b13e98b06cc52d29ae78f330d39b39c84ccec","sha256:7ca84b7ea6f26b5d02bf6eb3460c44db7b0a73538b5246275323d0c29626b9aa"],"state_sha256":"14a399b5558af49ae4ca5bc25d67f347b44e2685819c9b6b8e8c5f8e3c51f1db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJ+1THe8ju06Rq8+DVQqBWLSPc7sN+N82JdETXzItSUGZ+QW3fmPofaB0YRogQgbWIWwJnsRnJc5iuPtkHtGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:08:02.423413Z","bundle_sha256":"e09d10332cd51cb88a04c33bdbe15f58634f340d206c4bb7934787c4def8c402"}}