{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ANSISFYA4BYYU5KG3AM24W2544","short_pith_number":"pith:ANSISFYA","canonical_record":{"source":{"id":"2504.07957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"d10006d73d4c20e0efd8997c1f76e5ddf35b423b4f9ff9f958516bef263c4e8f","abstract_canon_sha256":"4e04c3ea9620dd2d10999bca9464184895673ccbbebc3598eb1fd55ceb9fb1ad"},"schema_version":"1.0"},"canonical_sha256":"0364891700e0718a7546d819ae5b5de7341fb7dc7e914466c24762d8863f35c6","source":{"kind":"arxiv","id":"2504.07957","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07957","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07957v2","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07957","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"ANSISFYA4BYY","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"ANSISFYA4BYYU5KG","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"ANSISFYA","created_at":"2026-07-05T10:54:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ANSISFYA4BYYU5KG3AM24W2544","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"d10006d73d4c20e0efd8997c1f76e5ddf35b423b4f9ff9f958516bef263c4e8f","abstract_canon_sha256":"4e04c3ea9620dd2d10999bca9464184895673ccbbebc3598eb1fd55ceb9fb1ad"},"schema_version":"1.0"},"canonical_sha256":"0364891700e0718a7546d819ae5b5de7341fb7dc7e914466c24762d8863f35c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:46.105847Z","signature_b64":"yC0DEhoNQirOfr//dHHQGSpwIow/JBww7SfewY4uI6Dq/sVHwKwyI+lOy4URl3YXKI/D7Lxj5bsa+DQEm+l6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0364891700e0718a7546d819ae5b5de7341fb7dc7e914466c24762d8863f35c6","last_reissued_at":"2026-07-05T10:54:46.105319Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:46.105319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07957","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":"2026-07-05T10:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OTvIeirdc7arYYnGnWeAkiJpVUSYFd/f/tmZI1rKydPxRQlCFNBBOOTkWI7KL1Jyvn0c9a5zNoGuqRzM5lLrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:51.317391Z"},"content_sha256":"7eff2e37bea8400997848e8fa4485fd1cdf18701c810c5276d3065689dff58c3","schema_version":"1.0","event_id":"sha256:7eff2e37bea8400997848e8fa4485fd1cdf18701c810c5276d3065689dff58c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ANSISFYA4BYYU5KG3AM24W2544","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-IFEngine: Towards Multimodal Instruction Following","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Pan Zhang, Shengyuan Ding, Shenxi Wu, Xiangyu Zhao, Xiaoyi Dong, Yuhang Cao, Yuhang Zang","submitted_at":"2025-04-10T17:59:12Z","abstract_excerpt":"The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data is scarce, the benchmarks are simple with atomic instructions, and the evaluation strategies are imprecise for tasks demanding exact output constraints. To address this, we present MM-IFEngine, an effective pipeline to generate high-quality image-instruction pairs. Our MM-IFEngine pipeline yields large-scale, diverse, and high-quality training data MM-IFInstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07957","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/2504.07957/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":"2026-07-05T10:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KfanDdjXXAtvaHkKDvsq25l1851GTrI79qWAFOub8HxuncnKPqQ32501veFViaFjgY25KY+7jV7I59sbBu7WAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:27:51.318293Z"},"content_sha256":"aebeb1756b53bbd21dc4cd290c43fc6a89b5d12fa4c0c60e1fb78cbeb3a2fc05","schema_version":"1.0","event_id":"sha256:aebeb1756b53bbd21dc4cd290c43fc6a89b5d12fa4c0c60e1fb78cbeb3a2fc05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ANSISFYA4BYYU5KG3AM24W2544/bundle.json","state_url":"https://pith.science/pith/ANSISFYA4BYYU5KG3AM24W2544/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ANSISFYA4BYYU5KG3AM24W2544/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":"2026-08-06T11:27:51Z","links":{"resolver":"https://pith.science/pith/ANSISFYA4BYYU5KG3AM24W2544","bundle":"https://pith.science/pith/ANSISFYA4BYYU5KG3AM24W2544/bundle.json","state":"https://pith.science/pith/ANSISFYA4BYYU5KG3AM24W2544/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ANSISFYA4BYYU5KG3AM24W2544/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ANSISFYA4BYYU5KG3AM24W2544","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":"4e04c3ea9620dd2d10999bca9464184895673ccbbebc3598eb1fd55ceb9fb1ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:12Z","title_canon_sha256":"d10006d73d4c20e0efd8997c1f76e5ddf35b423b4f9ff9f958516bef263c4e8f"},"schema_version":"1.0","source":{"id":"2504.07957","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07957","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07957v2","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07957","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"ANSISFYA4BYY","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"ANSISFYA4BYYU5KG","created_at":"2026-07-05T10:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"ANSISFYA","created_at":"2026-07-05T10:54:46Z"}],"graph_snapshots":[{"event_id":"sha256:aebeb1756b53bbd21dc4cd290c43fc6a89b5d12fa4c0c60e1fb78cbeb3a2fc05","target":"graph","created_at":"2026-07-05T10:54:46Z","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/2504.07957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data is scarce, the benchmarks are simple with atomic instructions, and the evaluation strategies are imprecise for tasks demanding exact output constraints. To address this, we present MM-IFEngine, an effective pipeline to generate high-quality image-instruction pairs. Our MM-IFEngine pipeline yields large-scale, diverse, and high-quality training data MM-IFInstr","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Pan Zhang, Shengyuan Ding, Shenxi Wu, Xiangyu Zhao, Xiaoyi Dong, Yuhang Cao, Yuhang Zang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:12Z","title":"MM-IFEngine: Towards Multimodal Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07957","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":"sha256:7eff2e37bea8400997848e8fa4485fd1cdf18701c810c5276d3065689dff58c3","target":"record","created_at":"2026-07-05T10:54:46Z","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":"4e04c3ea9620dd2d10999bca9464184895673ccbbebc3598eb1fd55ceb9fb1ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:12Z","title_canon_sha256":"d10006d73d4c20e0efd8997c1f76e5ddf35b423b4f9ff9f958516bef263c4e8f"},"schema_version":"1.0","source":{"id":"2504.07957","kind":"arxiv","version":2}},"canonical_sha256":"0364891700e0718a7546d819ae5b5de7341fb7dc7e914466c24762d8863f35c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0364891700e0718a7546d819ae5b5de7341fb7dc7e914466c24762d8863f35c6","first_computed_at":"2026-07-05T10:54:46.105319Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:46.105319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yC0DEhoNQirOfr//dHHQGSpwIow/JBww7SfewY4uI6Dq/sVHwKwyI+lOy4URl3YXKI/D7Lxj5bsa+DQEm+l6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:46.105847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07957","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eff2e37bea8400997848e8fa4485fd1cdf18701c810c5276d3065689dff58c3","sha256:aebeb1756b53bbd21dc4cd290c43fc6a89b5d12fa4c0c60e1fb78cbeb3a2fc05"],"state_sha256":"51048ea7b8eb31835a77f3700039c97f476e65f855587d3451de02322c68f212"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h08eWdP6LPIZ8GiOwsRdBjyrqvePkQHdEELAc6UFD6GQdt24YVbpBnm1RuydzSOLMYr06CMBYtguM7v9AtbtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:27:51.325844Z","bundle_sha256":"8f6e165e1d346c712b0a5905ddd06d1524504b74570da64d1cfa788391959980"}}