{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QNAWQZY66CQKEEYVBQYQQFWMFS","short_pith_number":"pith:QNAWQZY6","schema_version":"1.0","canonical_sha256":"834168671ef0a0a213150c310816cc2c9cda52391f98c7d992df1abd6f142da2","source":{"kind":"arxiv","id":"2606.22976","version":1},"attestation_state":"computed","paper":{"title":"Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cho Cholyeon, Purnamrita Sarkar, Sujay Sanghavi, Syamantak Kumar, Vansh Bansal","submitted_at":"2026-06-22T07:56:50Z","abstract_excerpt":"In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on random walk samples from a fixed graph. The graph or the transition kernel is never shown to the model explicitly and plays the role of latent structure in the sequences, albeit one that is controllable and can be used for quantitative evaluation. Thus, this framework enjoys a Sudoku-like validity check: verifying that an output is a valid walk and estimating the Markov kernel from the walks to measure distribution "},"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":"2606.22976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T07:56:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"976c733d86346ef223469ee35365376de756ed3cf34af4e79db93d89d0320fbf","abstract_canon_sha256":"a6655122e7891b8b87c6e330587de17f7ff70a49261375ca627966e36e259a97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:05.723237Z","signature_b64":"9n1TGV0SwnRqxIHz+UyJFDFPbOcB3ONGw0bI2loWr0kqAHBS7+MYZBdHobADt4Rr3EIqrtaAFq1+bcbXDOeQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"834168671ef0a0a213150c310816cc2c9cda52391f98c7d992df1abd6f142da2","last_reissued_at":"2026-06-23T03:14:05.722873Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:05.722873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cho Cholyeon, Purnamrita Sarkar, Sujay Sanghavi, Syamantak Kumar, Vansh Bansal","submitted_at":"2026-06-22T07:56:50Z","abstract_excerpt":"In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on random walk samples from a fixed graph. The graph or the transition kernel is never shown to the model explicitly and plays the role of latent structure in the sequences, albeit one that is controllable and can be used for quantitative evaluation. Thus, this framework enjoys a Sudoku-like validity check: verifying that an output is a valid walk and estimating the Markov kernel from the walks to measure distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22976","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/2606.22976/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":"2606.22976","created_at":"2026-06-23T03:14:05.722936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22976v1","created_at":"2026-06-23T03:14:05.722936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22976","created_at":"2026-06-23T03:14:05.722936+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNAWQZY66CQK","created_at":"2026-06-23T03:14:05.722936+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNAWQZY66CQKEEYV","created_at":"2026-06-23T03:14:05.722936+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNAWQZY6","created_at":"2026-06-23T03:14:05.722936+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/QNAWQZY66CQKEEYVBQYQQFWMFS","json":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS.json","graph_json":"https://pith.science/api/pith-number/QNAWQZY66CQKEEYVBQYQQFWMFS/graph.json","events_json":"https://pith.science/api/pith-number/QNAWQZY66CQKEEYVBQYQQFWMFS/events.json","paper":"https://pith.science/paper/QNAWQZY6"},"agent_actions":{"view_html":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS","download_json":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS.json","view_paper":"https://pith.science/paper/QNAWQZY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22976&json=true","fetch_graph":"https://pith.science/api/pith-number/QNAWQZY66CQKEEYVBQYQQFWMFS/graph.json","fetch_events":"https://pith.science/api/pith-number/QNAWQZY66CQKEEYVBQYQQFWMFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS/action/storage_attestation","attest_author":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS/action/author_attestation","sign_citation":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS/action/citation_signature","submit_replication":"https://pith.science/pith/QNAWQZY66CQKEEYVBQYQQFWMFS/action/replication_record"}},"created_at":"2026-06-23T03:14:05.722936+00:00","updated_at":"2026-06-23T03:14:05.722936+00:00"}