{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PELPJXJIKMPHKX7IA4QGYHVWRM","short_pith_number":"pith:PELPJXJI","schema_version":"1.0","canonical_sha256":"7916f4dd28531e755fe807206c1eb68b25c15306ea5659340d7f9c45a8091a8a","source":{"kind":"arxiv","id":"2606.19538","version":1},"attestation_state":"computed","paper":{"title":"ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ashim Dhor, Pin Yu Chen, Rasel Mondal","submitted_at":"2026-06-17T19:30:11Z","abstract_excerpt":"Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and content-dependent pairwise interaction -- and have remained mathematically distinct since their inception. We show that this fragmentation reflects not a fundamental diversity in how signals should be processed, but rather incomplete views of a single underlying mathematical object: a learnable integral transform. We introduce the Integral Transform Network (ITNet), a unified architecture built around a learnable kernel that depends jointly on positions and fe"},"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":"2606.19538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T19:30:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dfae9ba55102c308403949df332bb04d571839513c1506537d7c0513c72a1629","abstract_canon_sha256":"b8ba61cfadb85349cf08b3bacb362a746c70dad74d94985e7ec6291f1218be5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:28.169825Z","signature_b64":"LKmxffYSW++B7IxAv9Af5kG0RcWdMFnYFlqDxauWcccAz+DftT3FFKcWRyKA4jnFvbhIllMZL/yoWA3Ky0fRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7916f4dd28531e755fe807206c1eb68b25c15306ea5659340d7f9c45a8091a8a","last_reissued_at":"2026-06-19T16:12:28.169485Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:28.169485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ashim Dhor, Pin Yu Chen, Rasel Mondal","submitted_at":"2026-06-17T19:30:11Z","abstract_excerpt":"Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and content-dependent pairwise interaction -- and have remained mathematically distinct since their inception. We show that this fragmentation reflects not a fundamental diversity in how signals should be processed, but rather incomplete views of a single underlying mathematical object: a learnable integral transform. We introduce the Integral Transform Network (ITNet), a unified architecture built around a learnable kernel that depends jointly on positions and fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19538","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/2606.19538/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":"2606.19538","created_at":"2026-06-19T16:12:28.169546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19538v1","created_at":"2026-06-19T16:12:28.169546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19538","created_at":"2026-06-19T16:12:28.169546+00:00"},{"alias_kind":"pith_short_12","alias_value":"PELPJXJIKMPH","created_at":"2026-06-19T16:12:28.169546+00:00"},{"alias_kind":"pith_short_16","alias_value":"PELPJXJIKMPHKX7I","created_at":"2026-06-19T16:12:28.169546+00:00"},{"alias_kind":"pith_short_8","alias_value":"PELPJXJI","created_at":"2026-06-19T16:12:28.169546+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/PELPJXJIKMPHKX7IA4QGYHVWRM","json":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM.json","graph_json":"https://pith.science/api/pith-number/PELPJXJIKMPHKX7IA4QGYHVWRM/graph.json","events_json":"https://pith.science/api/pith-number/PELPJXJIKMPHKX7IA4QGYHVWRM/events.json","paper":"https://pith.science/paper/PELPJXJI"},"agent_actions":{"view_html":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM","download_json":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM.json","view_paper":"https://pith.science/paper/PELPJXJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19538&json=true","fetch_graph":"https://pith.science/api/pith-number/PELPJXJIKMPHKX7IA4QGYHVWRM/graph.json","fetch_events":"https://pith.science/api/pith-number/PELPJXJIKMPHKX7IA4QGYHVWRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM/action/storage_attestation","attest_author":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM/action/author_attestation","sign_citation":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM/action/citation_signature","submit_replication":"https://pith.science/pith/PELPJXJIKMPHKX7IA4QGYHVWRM/action/replication_record"}},"created_at":"2026-06-19T16:12:28.169546+00:00","updated_at":"2026-06-19T16:12:28.169546+00:00"}