{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KYW7EOFL37D5FWFO4YDZQZI73U","short_pith_number":"pith:KYW7EOFL","schema_version":"1.0","canonical_sha256":"562df238abdfc7d2d8aee60798651fdd0f427ae71d1034938c94d694981facf9","source":{"kind":"arxiv","id":"2605.28101","version":1},"attestation_state":"computed","paper":{"title":"EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Chong Jing, Junan Zhang, Zhizheng Wu, Zitong Lan","submitted_at":"2026-05-27T07:54:47Z","abstract_excerpt":"Predicting spatially varying Room Impulse Response (RIR) from sparse observations is a critical but highly challenging inverse problem for immersive spatial audio rendering. In this work, we present EIGENET, a geometry-informed multi-modal framework for few-shot novel view RIR prediction. At its core is a Cross-view Alternate-attention Transformer that iteratively refines local intra-view acoustic structures and global cross-view spatial relationships. We empirically demonstrate that this architecture is capable of making full use of the multi-view multi-modal context while performing spatial-"},"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":"2605.28101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T07:54:47Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"4a1d6374cfcb3b9298f23751f84f80c767f98ee9c078e44d3eaf98facc359e83","abstract_canon_sha256":"fdddb97c3e5d697b479343f1156b7ae41750ed2f53599d5ad5c3f6337dd986a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:58.834176Z","signature_b64":"7/1brBI3L7chXWJRJ6GB4oXisRK+M5N/9RMkzOC2RCfMO/dW0dqf7QYvJWpYH7rCb0lr/Lx2qCuuwamaczMnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"562df238abdfc7d2d8aee60798651fdd0f427ae71d1034938c94d694981facf9","last_reissued_at":"2026-05-28T01:04:58.833765Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:58.833765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Chong Jing, Junan Zhang, Zhizheng Wu, Zitong Lan","submitted_at":"2026-05-27T07:54:47Z","abstract_excerpt":"Predicting spatially varying Room Impulse Response (RIR) from sparse observations is a critical but highly challenging inverse problem for immersive spatial audio rendering. In this work, we present EIGENET, a geometry-informed multi-modal framework for few-shot novel view RIR prediction. At its core is a Cross-view Alternate-attention Transformer that iteratively refines local intra-view acoustic structures and global cross-view spatial relationships. We empirically demonstrate that this architecture is capable of making full use of the multi-view multi-modal context while performing spatial-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28101","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/2605.28101/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":"2605.28101","created_at":"2026-05-28T01:04:58.833830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28101v1","created_at":"2026-05-28T01:04:58.833830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28101","created_at":"2026-05-28T01:04:58.833830+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYW7EOFL37D5","created_at":"2026-05-28T01:04:58.833830+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYW7EOFL37D5FWFO","created_at":"2026-05-28T01:04:58.833830+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYW7EOFL","created_at":"2026-05-28T01:04:58.833830+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/KYW7EOFL37D5FWFO4YDZQZI73U","json":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U.json","graph_json":"https://pith.science/api/pith-number/KYW7EOFL37D5FWFO4YDZQZI73U/graph.json","events_json":"https://pith.science/api/pith-number/KYW7EOFL37D5FWFO4YDZQZI73U/events.json","paper":"https://pith.science/paper/KYW7EOFL"},"agent_actions":{"view_html":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U","download_json":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U.json","view_paper":"https://pith.science/paper/KYW7EOFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28101&json=true","fetch_graph":"https://pith.science/api/pith-number/KYW7EOFL37D5FWFO4YDZQZI73U/graph.json","fetch_events":"https://pith.science/api/pith-number/KYW7EOFL37D5FWFO4YDZQZI73U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U/action/storage_attestation","attest_author":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U/action/author_attestation","sign_citation":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U/action/citation_signature","submit_replication":"https://pith.science/pith/KYW7EOFL37D5FWFO4YDZQZI73U/action/replication_record"}},"created_at":"2026-05-28T01:04:58.833830+00:00","updated_at":"2026-05-28T01:04:58.833830+00:00"}