{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4YBE3JMV6PXEHD77FC4QQ3GJVK","short_pith_number":"pith:4YBE3JMV","schema_version":"1.0","canonical_sha256":"e6024da595f3ee438fff28b9086cc9aa91cae9b8b1232af57d9a9b2eb3a84b3a","source":{"kind":"arxiv","id":"2506.18129","version":1},"attestation_state":"computed","paper":{"title":"$\\phi^{\\infty}$: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bugra Kilictas, Faruk Alpay","submitted_at":"2025-06-22T18:27:39Z","abstract_excerpt":"We identify a critical vulnerability in autoregressive transformer language models where the em dash token induces recursive semantic drift, leading to clause boundary hallucination and embedding space entanglement. Through formal analysis of token-level perturbations in semantic lattices, we demonstrate that em dash insertion fundamentally alters the model's latent representations, causing compounding errors in long-form generation. We propose a novel solution combining symbolic clause purification via the phi-infinity operator with targeted embedding matrix realignment. Our approach enables "},"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":"2506.18129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-22T18:27:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4badbb0633bf80a9f20c01007c4e5afe747a68ae0a16836dcbe50643eac12bcd","abstract_canon_sha256":"3f62bde186180aab262ef110702ea7fb50fcd5307198dde7ff3f6e1065414e24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:29.192514Z","signature_b64":"LkZkeeodPgjLhhOzjVOw/vBxQJMfKdGxym9vHhosDTRHMXr4Mnq3UsUtFjkwC3CE8r6kuIG38mUPZl/FIErVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6024da595f3ee438fff28b9086cc9aa91cae9b8b1232af57d9a9b2eb3a84b3a","last_reissued_at":"2026-07-05T11:25:29.191956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:29.191956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\phi^{\\infty}$: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bugra Kilictas, Faruk Alpay","submitted_at":"2025-06-22T18:27:39Z","abstract_excerpt":"We identify a critical vulnerability in autoregressive transformer language models where the em dash token induces recursive semantic drift, leading to clause boundary hallucination and embedding space entanglement. Through formal analysis of token-level perturbations in semantic lattices, we demonstrate that em dash insertion fundamentally alters the model's latent representations, causing compounding errors in long-form generation. We propose a novel solution combining symbolic clause purification via the phi-infinity operator with targeted embedding matrix realignment. Our approach enables "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18129","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/2506.18129/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":"2506.18129","created_at":"2026-07-05T11:25:29.192018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18129v1","created_at":"2026-07-05T11:25:29.192018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18129","created_at":"2026-07-05T11:25:29.192018+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YBE3JMV6PXE","created_at":"2026-07-05T11:25:29.192018+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YBE3JMV6PXEHD77","created_at":"2026-07-05T11:25:29.192018+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YBE3JMV","created_at":"2026-07-05T11:25:29.192018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03774","citing_title":"Alpay Algebra IV: Symbiotic Semantics and the Fixed-Point Convergence of Observer Embeddings","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK","json":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK.json","graph_json":"https://pith.science/api/pith-number/4YBE3JMV6PXEHD77FC4QQ3GJVK/graph.json","events_json":"https://pith.science/api/pith-number/4YBE3JMV6PXEHD77FC4QQ3GJVK/events.json","paper":"https://pith.science/paper/4YBE3JMV"},"agent_actions":{"view_html":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK","download_json":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK.json","view_paper":"https://pith.science/paper/4YBE3JMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18129&json=true","fetch_graph":"https://pith.science/api/pith-number/4YBE3JMV6PXEHD77FC4QQ3GJVK/graph.json","fetch_events":"https://pith.science/api/pith-number/4YBE3JMV6PXEHD77FC4QQ3GJVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK/action/storage_attestation","attest_author":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK/action/author_attestation","sign_citation":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK/action/citation_signature","submit_replication":"https://pith.science/pith/4YBE3JMV6PXEHD77FC4QQ3GJVK/action/replication_record"}},"created_at":"2026-07-05T11:25:29.192018+00:00","updated_at":"2026-07-05T11:25:29.192018+00:00"}