{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4TUTXETLB57OB27HD4KX3IV7PY","short_pith_number":"pith:4TUTXETL","schema_version":"1.0","canonical_sha256":"e4e93b926b0f7ee0ebe71f157da2bf7e3833ef39495d31dd78afe49b388f3fe9","source":{"kind":"arxiv","id":"2510.19304","version":3},"attestation_state":"computed","paper":{"title":"Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Jaesik Yoon, Justin Deschenaux, Mingyu Jo, Sungjin Ahn","submitted_at":"2025-10-22T07:08:47Z","abstract_excerpt":"Discrete diffusion models offer a promising alternative to autoregressive generation through parallel decoding, but they suffer from a sampling wall: once categorical sampling occurs, rich distributional information collapses into one-hot vectors and cannot be propagated across steps, forcing subsequent steps to operate with limited information. To mitigate this problem, we introduce Loopholing, a novel and simple mechanism that preserves this information via a deterministic latent pathway, leading to Loopholing Discrete Diffusion Models (LDDMs). Trained efficiently with a self-conditioning st"},"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":"2510.19304","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-22T07:08:47Z","cross_cats_sorted":[],"title_canon_sha256":"cdb995384dca4acaf1e56c4c2963a68f4215b3327f6a645c44a01d40fde622b8","abstract_canon_sha256":"4da70eba6f193ef552a5b1960139b4d014aeddd19f55427637119dfcaa0b9f2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.753668Z","signature_b64":"e4VG0wiHeQroQ4HN26ZEfHp8hPTamrRiIhleTEEUvaCEAjlQAtn2E59z7WwbRi3+nhmybmJOZL9cRNjMI6Y8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4e93b926b0f7ee0ebe71f157da2bf7e3833ef39495d31dd78afe49b388f3fe9","last_reissued_at":"2026-05-18T03:09:33.753138Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.753138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Jaesik Yoon, Justin Deschenaux, Mingyu Jo, Sungjin Ahn","submitted_at":"2025-10-22T07:08:47Z","abstract_excerpt":"Discrete diffusion models offer a promising alternative to autoregressive generation through parallel decoding, but they suffer from a sampling wall: once categorical sampling occurs, rich distributional information collapses into one-hot vectors and cannot be propagated across steps, forcing subsequent steps to operate with limited information. To mitigate this problem, we introduce Loopholing, a novel and simple mechanism that preserves this information via a deterministic latent pathway, leading to Loopholing Discrete Diffusion Models (LDDMs). Trained efficiently with a self-conditioning st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.19304","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2510.19304","created_at":"2026-05-18T03:09:33.753215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.19304v3","created_at":"2026-05-18T03:09:33.753215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.19304","created_at":"2026-05-18T03:09:33.753215+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TUTXETLB57O","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TUTXETLB57OB27H","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TUTXETL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.26985","citing_title":"Simple Self-Conditioning Adaptation for Masked Diffusion Models","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY","json":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY.json","graph_json":"https://pith.science/api/pith-number/4TUTXETLB57OB27HD4KX3IV7PY/graph.json","events_json":"https://pith.science/api/pith-number/4TUTXETLB57OB27HD4KX3IV7PY/events.json","paper":"https://pith.science/paper/4TUTXETL"},"agent_actions":{"view_html":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY","download_json":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY.json","view_paper":"https://pith.science/paper/4TUTXETL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.19304&json=true","fetch_graph":"https://pith.science/api/pith-number/4TUTXETLB57OB27HD4KX3IV7PY/graph.json","fetch_events":"https://pith.science/api/pith-number/4TUTXETLB57OB27HD4KX3IV7PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY/action/storage_attestation","attest_author":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY/action/author_attestation","sign_citation":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY/action/citation_signature","submit_replication":"https://pith.science/pith/4TUTXETLB57OB27HD4KX3IV7PY/action/replication_record"}},"created_at":"2026-05-18T03:09:33.753215+00:00","updated_at":"2026-05-18T03:09:33.753215+00:00"}