{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3IVAMUJ3AWA7JRNU7NSS6AZWNE","short_pith_number":"pith:3IVAMUJ3","canonical_record":{"source":{"id":"2410.12332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T07:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"d924180336983f9815677f6d9abf7a0e4fc10467c1fef98afea193d1b322447d","abstract_canon_sha256":"56a33b57d2b269ce66824cdb1907e07ec5858e43c7d628eea6829cc3da92ad01"},"schema_version":"1.0"},"canonical_sha256":"da2a06513b0581f4c5b4fb652f03366903ff39df7f221b2a4fed01f846e78b17","source":{"kind":"arxiv","id":"2410.12332","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12332","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12332v2","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12332","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"3IVAMUJ3AWA7","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"3IVAMUJ3AWA7JRNU","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"3IVAMUJ3","created_at":"2026-07-05T11:40:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3IVAMUJ3AWA7JRNU7NSS6AZWNE","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T07:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"d924180336983f9815677f6d9abf7a0e4fc10467c1fef98afea193d1b322447d","abstract_canon_sha256":"56a33b57d2b269ce66824cdb1907e07ec5858e43c7d628eea6829cc3da92ad01"},"schema_version":"1.0"},"canonical_sha256":"da2a06513b0581f4c5b4fb652f03366903ff39df7f221b2a4fed01f846e78b17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:50.191789Z","signature_b64":"9rxKpX63AJWOw4p8KD0fCPfiyJ1LcqoMRpo1laklmylSSueWhmC2WmjR5Suho4JPoyEo2v6NzXneq59qcew/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2a06513b0581f4c5b4fb652f03366903ff39df7f221b2a4fed01f846e78b17","last_reissued_at":"2026-07-05T11:40:50.191289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:50.191289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12332","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A4TuZzN/GJRDOltFiA46wSoQsuhUxomYhyjDIWDSR7NKTKQ65RNNGPyc6V8hDVLHsaMqjA+bcZaHNUW6KkMyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:52:28.133135Z"},"content_sha256":"3ec8f385a042ee046c25b18b79bd6990bbbd7a2d6330e1ae1af6a1654e8239c8","schema_version":"1.0","event_id":"sha256:3ec8f385a042ee046c25b18b79bd6990bbbd7a2d6330e1ae1af6a1654e8239c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3IVAMUJ3AWA7JRNU7NSS6AZWNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Yi Yang, Yunqiu Xu","submitted_at":"2024-10-16T07:52:57Z","abstract_excerpt":"While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language problems beyond a single image warrant further exploration. To assess these unproven abilities of MLLMs, this paper proposes a new visual grounding task called multi-context visual grounding, which aims to localize instances of interest across multiple images based on open-ended text prompts. In order to facilitate this research, we construct a new dataset MC-Bench that features 2K high-quality and manually annotated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12332","kind":"arxiv","version":2},"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/2410.12332/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":"2026-07-05T11:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TV50H2kJjbWG8w6pgkozhSLiYKWifSq8Jo2lqlCWwXudWPST2gbOz5MsRREAies7nBvYIh02EZbzXfiEwPftBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:52:28.133438Z"},"content_sha256":"c2195e07706f645d73283adab13b17bd822f0855fdbd419de5dcf05333aaa9e7","schema_version":"1.0","event_id":"sha256:c2195e07706f645d73283adab13b17bd822f0855fdbd419de5dcf05333aaa9e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE/bundle.json","state_url":"https://pith.science/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE/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":"2026-08-05T12:52:28Z","links":{"resolver":"https://pith.science/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE","bundle":"https://pith.science/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE/bundle.json","state":"https://pith.science/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IVAMUJ3AWA7JRNU7NSS6AZWNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3IVAMUJ3AWA7JRNU7NSS6AZWNE","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":"56a33b57d2b269ce66824cdb1907e07ec5858e43c7d628eea6829cc3da92ad01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T07:52:57Z","title_canon_sha256":"d924180336983f9815677f6d9abf7a0e4fc10467c1fef98afea193d1b322447d"},"schema_version":"1.0","source":{"id":"2410.12332","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12332","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12332v2","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12332","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"3IVAMUJ3AWA7","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"3IVAMUJ3AWA7JRNU","created_at":"2026-07-05T11:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"3IVAMUJ3","created_at":"2026-07-05T11:40:50Z"}],"graph_snapshots":[{"event_id":"sha256:c2195e07706f645d73283adab13b17bd822f0855fdbd419de5dcf05333aaa9e7","target":"graph","created_at":"2026-07-05T11:40:50Z","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/2410.12332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language problems beyond a single image warrant further exploration. To assess these unproven abilities of MLLMs, this paper proposes a new visual grounding task called multi-context visual grounding, which aims to localize instances of interest across multiple images based on open-ended text prompts. In order to facilitate this research, we construct a new dataset MC-Bench that features 2K high-quality and manually annotated ","authors_text":"Linchao Zhu, Yi Yang, Yunqiu Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T07:52:57Z","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12332","kind":"arxiv","version":2},"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":"sha256:3ec8f385a042ee046c25b18b79bd6990bbbd7a2d6330e1ae1af6a1654e8239c8","target":"record","created_at":"2026-07-05T11:40:50Z","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":"56a33b57d2b269ce66824cdb1907e07ec5858e43c7d628eea6829cc3da92ad01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T07:52:57Z","title_canon_sha256":"d924180336983f9815677f6d9abf7a0e4fc10467c1fef98afea193d1b322447d"},"schema_version":"1.0","source":{"id":"2410.12332","kind":"arxiv","version":2}},"canonical_sha256":"da2a06513b0581f4c5b4fb652f03366903ff39df7f221b2a4fed01f846e78b17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2a06513b0581f4c5b4fb652f03366903ff39df7f221b2a4fed01f846e78b17","first_computed_at":"2026-07-05T11:40:50.191289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:50.191289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9rxKpX63AJWOw4p8KD0fCPfiyJ1LcqoMRpo1laklmylSSueWhmC2WmjR5Suho4JPoyEo2v6NzXneq59qcew/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:50.191789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12332","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ec8f385a042ee046c25b18b79bd6990bbbd7a2d6330e1ae1af6a1654e8239c8","sha256:c2195e07706f645d73283adab13b17bd822f0855fdbd419de5dcf05333aaa9e7"],"state_sha256":"fc2f02c0fbfc6aab85f5dffd98ab428cf07e492db6015986886757d64476d3a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cOa4ubEvn+aIR+AREO/0JhgAW1zIUbeWsujwpZKYOER4w8ie0d0fTDM2d6EEibIWhozai42oA1uUIDtZs/d9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:52:28.137033Z","bundle_sha256":"ebaadfcd1081de36064fb5bb7a79751e4d6bc1dd2b31aef9335b30d61a6ab7ab"}}