{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X6TGSR66UEQNT2ITCJJ3CNFNZX","short_pith_number":"pith:X6TGSR66","schema_version":"1.0","canonical_sha256":"bfa66947dea120d9e9131253b134adcde33eb9e891f74f2170a6cdb26b0c63ca","source":{"kind":"arxiv","id":"2507.00068","version":1},"attestation_state":"computed","paper":{"title":"MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Daniel Tang, Ziqi Zhong","submitted_at":"2025-06-28T12:12:06Z","abstract_excerpt":"While multi-modal learning has advanced significantly, current approaches often treat modalities separately, creating inconsistencies in representation and reasoning. We introduce MANTA (Multi-modal Abstraction and Normalization via Textual Alignment), a theoretically-grounded framework that unifies visual and auditory inputs into a structured textual space for seamless processing with large language models. MANTA addresses four key challenges: (1) semantic alignment across modalities with information-theoretic optimization, (2) adaptive temporal synchronization for varying information densiti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.00068","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T12:12:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c849808806b63240495524f30f2801f5b74ad6f1226b0a05af5b6f7699eaa6bc","abstract_canon_sha256":"c548f530bb7351fcdd410b1df9f28e956fa31cb4f8bce24b8ecd5bfc3775e49c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:04.599789Z","signature_b64":"pwYPohK6pfViYhRjoCwaWR0LqRbnQy6n+eA25d/K3/UJEvDJPosQUV0oAFmOIGhzkewlnTg37QQxQFfdpEIYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa66947dea120d9e9131253b134adcde33eb9e891f74f2170a6cdb26b0c63ca","last_reissued_at":"2026-07-05T11:30:04.599311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:04.599311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Daniel Tang, Ziqi Zhong","submitted_at":"2025-06-28T12:12:06Z","abstract_excerpt":"While multi-modal learning has advanced significantly, current approaches often treat modalities separately, creating inconsistencies in representation and reasoning. We introduce MANTA (Multi-modal Abstraction and Normalization via Textual Alignment), a theoretically-grounded framework that unifies visual and auditory inputs into a structured textual space for seamless processing with large language models. MANTA addresses four key challenges: (1) semantic alignment across modalities with information-theoretic optimization, (2) adaptive temporal synchronization for varying information densiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00068","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/2507.00068/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.00068","created_at":"2026-07-05T11:30:04.599377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00068v1","created_at":"2026-07-05T11:30:04.599377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00068","created_at":"2026-07-05T11:30:04.599377+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6TGSR66UEQN","created_at":"2026-07-05T11:30:04.599377+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6TGSR66UEQNT2IT","created_at":"2026-07-05T11:30:04.599377+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6TGSR66","created_at":"2026-07-05T11:30:04.599377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX","json":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX.json","graph_json":"https://pith.science/api/pith-number/X6TGSR66UEQNT2ITCJJ3CNFNZX/graph.json","events_json":"https://pith.science/api/pith-number/X6TGSR66UEQNT2ITCJJ3CNFNZX/events.json","paper":"https://pith.science/paper/X6TGSR66"},"agent_actions":{"view_html":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX","download_json":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX.json","view_paper":"https://pith.science/paper/X6TGSR66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00068&json=true","fetch_graph":"https://pith.science/api/pith-number/X6TGSR66UEQNT2ITCJJ3CNFNZX/graph.json","fetch_events":"https://pith.science/api/pith-number/X6TGSR66UEQNT2ITCJJ3CNFNZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX/action/storage_attestation","attest_author":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX/action/author_attestation","sign_citation":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX/action/citation_signature","submit_replication":"https://pith.science/pith/X6TGSR66UEQNT2ITCJJ3CNFNZX/action/replication_record"}},"created_at":"2026-07-05T11:30:04.599377+00:00","updated_at":"2026-07-05T11:30:04.599377+00:00"}