{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:47O4EWEUBWWFCFPOCR5E4N7FM2","short_pith_number":"pith:47O4EWEU","canonical_record":{"source":{"id":"2406.11403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T10:45:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a1e3875217a172233dc0c44697cb11423d3d810ff860c3e18165d6d95e667881","abstract_canon_sha256":"1deb4aac64b035857c2248943e8e4672754977c2acbbeb29fc9563cded01a92b"},"schema_version":"1.0"},"canonical_sha256":"e7ddc258940dac5115ee147a4e37e566a895dca68cad0ae5dc4be810b019539c","source":{"kind":"arxiv","id":"2406.11403","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11403","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11403v2","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11403","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"47O4EWEUBWWF","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"47O4EWEUBWWFCFPO","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"47O4EWEU","created_at":"2026-07-05T10:09:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:47O4EWEUBWWFCFPOCR5E4N7FM2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T10:45:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a1e3875217a172233dc0c44697cb11423d3d810ff860c3e18165d6d95e667881","abstract_canon_sha256":"1deb4aac64b035857c2248943e8e4672754977c2acbbeb29fc9563cded01a92b"},"schema_version":"1.0"},"canonical_sha256":"e7ddc258940dac5115ee147a4e37e566a895dca68cad0ae5dc4be810b019539c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:44.756516Z","signature_b64":"jcGkJ3nOETfovP1ozYtLP8uPmk6O28C80MIGLE3iOJekDTtxIO8bWDAZlIqR6vLjQy87lgdr56Yj1H2zERzMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7ddc258940dac5115ee147a4e37e566a895dca68cad0ae5dc4be810b019539c","last_reissued_at":"2026-07-05T10:09:44.756056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:44.756056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11403","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":"2026-07-05T10:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gdf8bzrdoVhb7W9w0iREDWiwMJyJ88Wq9MwbSZXzLy4uHu4+5kp9o9YCaaZJqHI2QIoj0/TfuS7hgqkYYfAGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:29.515816Z"},"content_sha256":"6ebe9bc156fefc28bdf16f63e6062eb781203d0d701619a5407a971542d85fbb","schema_version":"1.0","event_id":"sha256:6ebe9bc156fefc28bdf16f63e6062eb781203d0d701619a5407a971542d85fbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:47O4EWEUBWWFCFPOCR5E4N7FM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Franz Louis Cesista","submitted_at":"2024-06-17T10:45:47Z","abstract_excerpt":"Multimodal Foundation Models (MMFMs) have demonstrated strong performance in both computer vision and natural language processing tasks. However, their performance diminishes in tasks that require a high degree of integration between these modalities, such as document understanding. Moreover, finetuning these models and deploying them requires significantly more compute and more engineering effort than unimodal models. In this work, we present Multimodal Structured Generation, a framework that forces (frozen) MMFMs to produce outputs in a strictly structured format by applying hard constraints"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11403","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/2406.11403/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":"2026-07-05T10:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d6piadn3plrVHtWO1PagM1t0lTBkgSsW90ZkVamcr/RAxkwSoTfVUNTDKkwvXHyrn5jtp4Qe5+H2bAUGTZpoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:29.516337Z"},"content_sha256":"92413bb8f562562025d70fafbc891b871d48b3afe7c1a38a68fdee2e091e44ff","schema_version":"1.0","event_id":"sha256:92413bb8f562562025d70fafbc891b871d48b3afe7c1a38a68fdee2e091e44ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47O4EWEUBWWFCFPOCR5E4N7FM2/bundle.json","state_url":"https://pith.science/pith/47O4EWEUBWWFCFPOCR5E4N7FM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47O4EWEUBWWFCFPOCR5E4N7FM2/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":"2026-08-04T19:05:29Z","links":{"resolver":"https://pith.science/pith/47O4EWEUBWWFCFPOCR5E4N7FM2","bundle":"https://pith.science/pith/47O4EWEUBWWFCFPOCR5E4N7FM2/bundle.json","state":"https://pith.science/pith/47O4EWEUBWWFCFPOCR5E4N7FM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47O4EWEUBWWFCFPOCR5E4N7FM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:47O4EWEUBWWFCFPOCR5E4N7FM2","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":"1deb4aac64b035857c2248943e8e4672754977c2acbbeb29fc9563cded01a92b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T10:45:47Z","title_canon_sha256":"a1e3875217a172233dc0c44697cb11423d3d810ff860c3e18165d6d95e667881"},"schema_version":"1.0","source":{"id":"2406.11403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11403","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11403v2","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11403","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"47O4EWEUBWWF","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"47O4EWEUBWWFCFPO","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"47O4EWEU","created_at":"2026-07-05T10:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:92413bb8f562562025d70fafbc891b871d48b3afe7c1a38a68fdee2e091e44ff","target":"graph","created_at":"2026-07-05T10:09:44Z","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/2406.11403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Foundation Models (MMFMs) have demonstrated strong performance in both computer vision and natural language processing tasks. However, their performance diminishes in tasks that require a high degree of integration between these modalities, such as document understanding. Moreover, finetuning these models and deploying them requires significantly more compute and more engineering effort than unimodal models. In this work, we present Multimodal Structured Generation, a framework that forces (frozen) MMFMs to produce outputs in a strictly structured format by applying hard constraints","authors_text":"Franz Louis Cesista","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T10:45:47Z","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11403","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":"sha256:6ebe9bc156fefc28bdf16f63e6062eb781203d0d701619a5407a971542d85fbb","target":"record","created_at":"2026-07-05T10:09:44Z","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":"1deb4aac64b035857c2248943e8e4672754977c2acbbeb29fc9563cded01a92b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T10:45:47Z","title_canon_sha256":"a1e3875217a172233dc0c44697cb11423d3d810ff860c3e18165d6d95e667881"},"schema_version":"1.0","source":{"id":"2406.11403","kind":"arxiv","version":2}},"canonical_sha256":"e7ddc258940dac5115ee147a4e37e566a895dca68cad0ae5dc4be810b019539c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7ddc258940dac5115ee147a4e37e566a895dca68cad0ae5dc4be810b019539c","first_computed_at":"2026-07-05T10:09:44.756056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:44.756056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jcGkJ3nOETfovP1ozYtLP8uPmk6O28C80MIGLE3iOJekDTtxIO8bWDAZlIqR6vLjQy87lgdr56Yj1H2zERzMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:44.756516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ebe9bc156fefc28bdf16f63e6062eb781203d0d701619a5407a971542d85fbb","sha256:92413bb8f562562025d70fafbc891b871d48b3afe7c1a38a68fdee2e091e44ff"],"state_sha256":"9622ec7abd1f2e142d559ffd22222d699fcb5dd25057004f5cecb63ebf13ded5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"98YxLcs3WikHGiS3dBvSluL6Xt5sCDeftVEKhEiLMb6WYPIUAwR6etp5oJWiBO2DGEDblX8t50fQxR2Yg2QnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:05:29.520379Z","bundle_sha256":"e0d1249eb51409f400e21c55cb1e0046fecc24def83fa15e7a2c00380c1de9c4"}}