{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZCO65PV6NGOUBXN7ZV2NGWR4DP","short_pith_number":"pith:ZCO65PV6","schema_version":"1.0","canonical_sha256":"c89deebebe699d40ddbfcd74d35a3c1bdb65e699d2dcf9fa95c30a99fbf78615","source":{"kind":"arxiv","id":"2605.24124","version":1},"attestation_state":"computed","paper":{"title":"A generative pre-trained transformer with Kerr-soliton attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"physics.optics","authors_text":"Lindell M. Williams, Scott B. Papp, Yan Jin","submitted_at":"2026-05-22T18:34:06Z","abstract_excerpt":"Artificial intelligence systems, particularly through generative pre-trained transformers (GPTs), have enabled capability-rich language models, but their operation incurs substantial costs in digital computation, memory, and data movement. Attention is a core operation in GPTs that computes context-dependent weights for input tokens. Since deep-learning models are defined by compositions of nonlinear transformations, identifying physical systems that can realize them offers a pathway to higher efficiency. Here, we introduce Kerr-soliton attention, harnessing driven-dissipative nonlinear dynami"},"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":"2605.24124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.optics","submitted_at":"2026-05-22T18:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"a9c814ae3ad371db1994f925b3fd9b7fae155771c38e79f393274e9d58114691","abstract_canon_sha256":"926de1fbe11ac56ebf8d85a99db8e7afee43e03fcb27feb0cf9567a1875ae5a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:47.630193Z","signature_b64":"u3r9YMgsa4cRg9NgagVyyAlomi2ZCV8YfBZlp4NJO5XeTmgkvwhcf8tZ62IgdYG3CKvKYs719EHoUMHYlhauAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c89deebebe699d40ddbfcd74d35a3c1bdb65e699d2dcf9fa95c30a99fbf78615","last_reissued_at":"2026-05-26T01:02:47.629452Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:47.629452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A generative pre-trained transformer with Kerr-soliton attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"physics.optics","authors_text":"Lindell M. Williams, Scott B. Papp, Yan Jin","submitted_at":"2026-05-22T18:34:06Z","abstract_excerpt":"Artificial intelligence systems, particularly through generative pre-trained transformers (GPTs), have enabled capability-rich language models, but their operation incurs substantial costs in digital computation, memory, and data movement. Attention is a core operation in GPTs that computes context-dependent weights for input tokens. Since deep-learning models are defined by compositions of nonlinear transformations, identifying physical systems that can realize them offers a pathway to higher efficiency. Here, we introduce Kerr-soliton attention, harnessing driven-dissipative nonlinear dynami"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24124","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/2605.24124/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":"2605.24124","created_at":"2026-05-26T01:02:47.629565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24124v1","created_at":"2026-05-26T01:02:47.629565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24124","created_at":"2026-05-26T01:02:47.629565+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCO65PV6NGOU","created_at":"2026-05-26T01:02:47.629565+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCO65PV6NGOUBXN7","created_at":"2026-05-26T01:02:47.629565+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCO65PV6","created_at":"2026-05-26T01:02:47.629565+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/ZCO65PV6NGOUBXN7ZV2NGWR4DP","json":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP.json","graph_json":"https://pith.science/api/pith-number/ZCO65PV6NGOUBXN7ZV2NGWR4DP/graph.json","events_json":"https://pith.science/api/pith-number/ZCO65PV6NGOUBXN7ZV2NGWR4DP/events.json","paper":"https://pith.science/paper/ZCO65PV6"},"agent_actions":{"view_html":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP","download_json":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP.json","view_paper":"https://pith.science/paper/ZCO65PV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24124&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCO65PV6NGOUBXN7ZV2NGWR4DP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCO65PV6NGOUBXN7ZV2NGWR4DP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP/action/storage_attestation","attest_author":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP/action/author_attestation","sign_citation":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP/action/citation_signature","submit_replication":"https://pith.science/pith/ZCO65PV6NGOUBXN7ZV2NGWR4DP/action/replication_record"}},"created_at":"2026-05-26T01:02:47.629565+00:00","updated_at":"2026-05-26T01:02:47.629565+00:00"}