{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZXLNVFA3BKAPN6I3OFDQNSSFZT","short_pith_number":"pith:ZXLNVFA3","schema_version":"1.0","canonical_sha256":"cdd6da941b0a80f6f91b714706ca45cce6f76dbc80a310edea7c72b38dde6a1f","source":{"kind":"arxiv","id":"2508.20211","version":1},"attestation_state":"computed","paper":{"title":"What can we learn from signals and systems in a transformer? Insights for probabilistic modeling and inference architecture","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.PR"],"primary_cat":"cs.LG","authors_text":"Heng-Sheng Chang, Prashant G. Mehta","submitted_at":"2025-08-27T18:37:55Z","abstract_excerpt":"In the 1940s, Wiener introduced a linear predictor, where the future prediction is computed by linearly combining the past data. A transformer generalizes this idea: it is a nonlinear predictor where the next-token prediction is computed by nonlinearly combining the past tokens. In this essay, we present a probabilistic model that interprets transformer signals as surrogates of conditional measures, and layer operations as fixed-point updates. An explicit form of the fixed-point update is described for the special case when the probabilistic model is a hidden Markov model (HMM). In part, this "},"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":"2508.20211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T18:37:55Z","cross_cats_sorted":["cs.SY","eess.SY","math.PR"],"title_canon_sha256":"4ee4fb34366508a9d4d1ad76665b4b49cef2df94e1e4a55555acfaa150e18283","abstract_canon_sha256":"2bb3e62a5344ce48bac22bca550174256694d55d5bcc56d3ce322ca5fcfff183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:31.388166Z","signature_b64":"ke3qr/EacqDgPM5PyYmIegnYAEdWyIw2H50draPbHT+ryll04TjPMBOBJ4sxeQQuz9V0oIWOn0noxH9OywQXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdd6da941b0a80f6f91b714706ca45cce6f76dbc80a310edea7c72b38dde6a1f","last_reissued_at":"2026-07-05T12:00:31.387672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:31.387672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What can we learn from signals and systems in a transformer? Insights for probabilistic modeling and inference architecture","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.PR"],"primary_cat":"cs.LG","authors_text":"Heng-Sheng Chang, Prashant G. Mehta","submitted_at":"2025-08-27T18:37:55Z","abstract_excerpt":"In the 1940s, Wiener introduced a linear predictor, where the future prediction is computed by linearly combining the past data. A transformer generalizes this idea: it is a nonlinear predictor where the next-token prediction is computed by nonlinearly combining the past tokens. In this essay, we present a probabilistic model that interprets transformer signals as surrogates of conditional measures, and layer operations as fixed-point updates. An explicit form of the fixed-point update is described for the special case when the probabilistic model is a hidden Markov model (HMM). In part, this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20211","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/2508.20211/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":"2508.20211","created_at":"2026-07-05T12:00:31.387729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20211v1","created_at":"2026-07-05T12:00:31.387729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20211","created_at":"2026-07-05T12:00:31.387729+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXLNVFA3BKAP","created_at":"2026-07-05T12:00:31.387729+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXLNVFA3BKAPN6I3","created_at":"2026-07-05T12:00:31.387729+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXLNVFA3","created_at":"2026-07-05T12:00:31.387729+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/ZXLNVFA3BKAPN6I3OFDQNSSFZT","json":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT.json","graph_json":"https://pith.science/api/pith-number/ZXLNVFA3BKAPN6I3OFDQNSSFZT/graph.json","events_json":"https://pith.science/api/pith-number/ZXLNVFA3BKAPN6I3OFDQNSSFZT/events.json","paper":"https://pith.science/paper/ZXLNVFA3"},"agent_actions":{"view_html":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT","download_json":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT.json","view_paper":"https://pith.science/paper/ZXLNVFA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20211&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXLNVFA3BKAPN6I3OFDQNSSFZT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXLNVFA3BKAPN6I3OFDQNSSFZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT/action/storage_attestation","attest_author":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT/action/author_attestation","sign_citation":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT/action/citation_signature","submit_replication":"https://pith.science/pith/ZXLNVFA3BKAPN6I3OFDQNSSFZT/action/replication_record"}},"created_at":"2026-07-05T12:00:31.387729+00:00","updated_at":"2026-07-05T12:00:31.387729+00:00"}