{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NATOKERNKSO376EKHORWGTZWTN","short_pith_number":"pith:NATOKERN","canonical_record":{"source":{"id":"2407.08739","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"ef6e07a0965546245feb02e894730a9cbab887f62b7346a75a92e6724ed4c700","abstract_canon_sha256":"598dacda624ee94e962f48cbf8ec1ad51a6714ea21acfd07234fa61ba5fdd2f8"},"schema_version":"1.0"},"canonical_sha256":"6826e5122d549dbff88a3ba3634f369b41acafdd21f33a83d0d09e692e2bfd6e","source":{"kind":"arxiv","id":"2407.08739","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08739","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08739v2","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08739","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_12","alias_value":"NATOKERNKSO3","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_16","alias_value":"NATOKERNKSO376EK","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_8","alias_value":"NATOKERN","created_at":"2026-07-05T09:29:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NATOKERNKSO376EKHORWGTZWTN","target":"record","payload":{"canonical_record":{"source":{"id":"2407.08739","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"ef6e07a0965546245feb02e894730a9cbab887f62b7346a75a92e6724ed4c700","abstract_canon_sha256":"598dacda624ee94e962f48cbf8ec1ad51a6714ea21acfd07234fa61ba5fdd2f8"},"schema_version":"1.0"},"canonical_sha256":"6826e5122d549dbff88a3ba3634f369b41acafdd21f33a83d0d09e692e2bfd6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:49.658861Z","signature_b64":"rkjcPawSSs3HrvimfhJRuYQo7uAJ44AwyiAszujDj9TltKPnAXmvPUrrm5/ui/skB/U4kRFCo0q498f3c/cBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6826e5122d549dbff88a3ba3634f369b41acafdd21f33a83d0d09e692e2bfd6e","last_reissued_at":"2026-07-05T09:29:49.658383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:49.658383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.08739","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":"2026-07-05T09:29:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8Aq3J1xkJBLoxqQbdKTKCKrE7RusAIahC++NtjR+NjnXG8wH+cmOLtsEblrOqcy/9UlbC+LiLhTL9H05p/3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:44:48.834178Z"},"content_sha256":"19c32db54ab52569769ca222f549702eb76a9f59526fda8868930c956c5f6530","schema_version":"1.0","event_id":"sha256:19c32db54ab52569769ca222f549702eb76a9f59526fda8868930c956c5f6530"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NATOKERNKSO376EKHORWGTZWTN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Bin Wei, Chengzhuo Tong, Chunyuan Li, Dongzhi Jiang, Hongsheng Li, Jiaming Liu, Peng Gao, Renrui Zhang, Shanghang Zhang, Shicheng Li, Xinyu Wei, Yichi Zhang, Ziyu Guo","submitted_at":"2024-07-11T17:59:47Z","abstract_excerpt":"The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws forth an urgent demand for an effective training paradigm and a large-scale, comprehensive dataset with detailed CoT rationales, which is challenging to collect and costly to annotate manually. To tackle this issue, we propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08739","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/2407.08739/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":"2026-07-05T09:29:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5I8Bl658wO/4J9w4FBo9sTQwqvB//LDNPXfWTIjrnIgHIlgBC+F6RbOnyCFd/4DTBROj0ThhVMYDYViNaf1oAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:44:48.834786Z"},"content_sha256":"a594f014e4a066edebf1c0bc451d1a7b54ab45d45f3e408eadd8cd022427ef18","schema_version":"1.0","event_id":"sha256:a594f014e4a066edebf1c0bc451d1a7b54ab45d45f3e408eadd8cd022427ef18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NATOKERNKSO376EKHORWGTZWTN/bundle.json","state_url":"https://pith.science/pith/NATOKERNKSO376EKHORWGTZWTN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NATOKERNKSO376EKHORWGTZWTN/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":"2026-08-19T02:44:48Z","links":{"resolver":"https://pith.science/pith/NATOKERNKSO376EKHORWGTZWTN","bundle":"https://pith.science/pith/NATOKERNKSO376EKHORWGTZWTN/bundle.json","state":"https://pith.science/pith/NATOKERNKSO376EKHORWGTZWTN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NATOKERNKSO376EKHORWGTZWTN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NATOKERNKSO376EKHORWGTZWTN","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":"598dacda624ee94e962f48cbf8ec1ad51a6714ea21acfd07234fa61ba5fdd2f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:59:47Z","title_canon_sha256":"ef6e07a0965546245feb02e894730a9cbab887f62b7346a75a92e6724ed4c700"},"schema_version":"1.0","source":{"id":"2407.08739","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08739","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08739v2","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08739","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_12","alias_value":"NATOKERNKSO3","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_16","alias_value":"NATOKERNKSO376EK","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_8","alias_value":"NATOKERN","created_at":"2026-07-05T09:29:49Z"}],"graph_snapshots":[{"event_id":"sha256:a594f014e4a066edebf1c0bc451d1a7b54ab45d45f3e408eadd8cd022427ef18","target":"graph","created_at":"2026-07-05T09:29:49Z","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/2407.08739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws forth an urgent demand for an effective training paradigm and a large-scale, comprehensive dataset with detailed CoT rationales, which is challenging to collect and costly to annotate manually. To tackle this issue, we propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathema","authors_text":"Aojun Zhou, Bin Wei, Chengzhuo Tong, Chunyuan Li, Dongzhi Jiang, Hongsheng Li, Jiaming Liu, Peng Gao, Renrui Zhang, Shanghang Zhang, Shicheng Li, Xinyu Wei, Yichi Zhang, Ziyu Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:59:47Z","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08739","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":"sha256:19c32db54ab52569769ca222f549702eb76a9f59526fda8868930c956c5f6530","target":"record","created_at":"2026-07-05T09:29:49Z","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":"598dacda624ee94e962f48cbf8ec1ad51a6714ea21acfd07234fa61ba5fdd2f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:59:47Z","title_canon_sha256":"ef6e07a0965546245feb02e894730a9cbab887f62b7346a75a92e6724ed4c700"},"schema_version":"1.0","source":{"id":"2407.08739","kind":"arxiv","version":2}},"canonical_sha256":"6826e5122d549dbff88a3ba3634f369b41acafdd21f33a83d0d09e692e2bfd6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6826e5122d549dbff88a3ba3634f369b41acafdd21f33a83d0d09e692e2bfd6e","first_computed_at":"2026-07-05T09:29:49.658383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:49.658383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rkjcPawSSs3HrvimfhJRuYQo7uAJ44AwyiAszujDj9TltKPnAXmvPUrrm5/ui/skB/U4kRFCo0q498f3c/cBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:49.658861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08739","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19c32db54ab52569769ca222f549702eb76a9f59526fda8868930c956c5f6530","sha256:a594f014e4a066edebf1c0bc451d1a7b54ab45d45f3e408eadd8cd022427ef18"],"state_sha256":"3b552d27eac109ecac9459eaf30df10a93dc234b7c69e57eaa9c1693411788f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXRpD8vv48mK0GdE053DnvEHgKuXMkalowzmgHfgNgiclDlIwi7SqsVmpNt2biltR0O6vk22cueR+BuxYeMlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:44:48.838374Z","bundle_sha256":"6d4fb6fcb04a30d4734897ffd0eed7e4867b85459bc89fa8d6688f73a4b6487c"}}