{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EZBMFK2TZQ5CDK2I7DCWWTQVOX","short_pith_number":"pith:EZBMFK2T","schema_version":"1.0","canonical_sha256":"2642c2ab53cc3a21ab48f8c56b4e1575f9cc1ee6ab467a9b2d7693a42f758075","source":{"kind":"arxiv","id":"2601.14776","version":3},"attestation_state":"computed","paper":{"title":"M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoqing Chu, Jie Zhao, Junming Zhang, Wei Pan, Xiaofan Yang, Xuanming Cao, Yubin Liu, Zhuoqi Man","submitted_at":"2026-01-21T08:55:07Z","abstract_excerpt":"Recent advances in multi-modal detection have significantly improved detection accuracy in challenging environments (e.g., low light, overexposure). By integrating RGB with modalities such as thermal and depth, multi-modal fusion increases data redundancy and system robustness. However, significant challenges remain in effectively extracting task-relevant information both within and across modalities, as well as in achieving precise cross-modal alignment. While CNNs excel at feature extraction, they are limited by constrained receptive fields, strong inductive biases, and difficulty in capturi"},"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":"2601.14776","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-21T08:55:07Z","cross_cats_sorted":[],"title_canon_sha256":"d09f10769568cf26f319f580ae5ef62721aaa24307bbcf647ace2904cfeefb94","abstract_canon_sha256":"064661f0860e61a3d361821023ed15de1dd2796ecd796a5b75a74f1365520719"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:20:53.737168Z","signature_b64":"lCKPUAGtf04HCI2cpZIzYMFwPjKG9YGYgYF0Jf+V4Di6R1FQGHBqj9QE8d2hzZx0cJc4ziVFL/fYRvzrr+goAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2642c2ab53cc3a21ab48f8c56b4e1575f9cc1ee6ab467a9b2d7693a42f758075","last_reissued_at":"2026-07-15T01:20:53.736277Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:20:53.736277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoqing Chu, Jie Zhao, Junming Zhang, Wei Pan, Xiaofan Yang, Xuanming Cao, Yubin Liu, Zhuoqi Man","submitted_at":"2026-01-21T08:55:07Z","abstract_excerpt":"Recent advances in multi-modal detection have significantly improved detection accuracy in challenging environments (e.g., low light, overexposure). By integrating RGB with modalities such as thermal and depth, multi-modal fusion increases data redundancy and system robustness. However, significant challenges remain in effectively extracting task-relevant information both within and across modalities, as well as in achieving precise cross-modal alignment. While CNNs excel at feature extraction, they are limited by constrained receptive fields, strong inductive biases, and difficulty in capturi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14776","kind":"arxiv","version":3},"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/2601.14776/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":"2601.14776","created_at":"2026-07-15T01:20:53.736701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.14776v3","created_at":"2026-07-15T01:20:53.736701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14776","created_at":"2026-07-15T01:20:53.736701+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZBMFK2TZQ5C","created_at":"2026-07-15T01:20:53.736701+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZBMFK2TZQ5CDK2I","created_at":"2026-07-15T01:20:53.736701+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZBMFK2T","created_at":"2026-07-15T01:20:53.736701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06205","citing_title":"CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX","json":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX.json","graph_json":"https://pith.science/api/pith-number/EZBMFK2TZQ5CDK2I7DCWWTQVOX/graph.json","events_json":"https://pith.science/api/pith-number/EZBMFK2TZQ5CDK2I7DCWWTQVOX/events.json","paper":"https://pith.science/paper/EZBMFK2T"},"agent_actions":{"view_html":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX","download_json":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX.json","view_paper":"https://pith.science/paper/EZBMFK2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.14776&json=true","fetch_graph":"https://pith.science/api/pith-number/EZBMFK2TZQ5CDK2I7DCWWTQVOX/graph.json","fetch_events":"https://pith.science/api/pith-number/EZBMFK2TZQ5CDK2I7DCWWTQVOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX/action/storage_attestation","attest_author":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX/action/author_attestation","sign_citation":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX/action/citation_signature","submit_replication":"https://pith.science/pith/EZBMFK2TZQ5CDK2I7DCWWTQVOX/action/replication_record"}},"created_at":"2026-07-15T01:20:53.736701+00:00","updated_at":"2026-07-15T01:20:53.736701+00:00"}