{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQLHGRNBAMZWAXYCYQEGKEIZT5","short_pith_number":"pith:QQLHGRNB","schema_version":"1.0","canonical_sha256":"84167345a10333605f02c4086511199f7fa274edef9bd191b51bc5d58c555b4a","source":{"kind":"arxiv","id":"2509.05056","version":1},"attestation_state":"computed","paper":{"title":"Masked Diffusion Language Models with Frequency-Informed Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandros Potamianos, Despoina Kosmopoulou, Efthymios Georgiou, Georgios Paraskevopoulos, Vaggelis Dorovatas","submitted_at":"2025-09-05T12:35:06Z","abstract_excerpt":"We present a masked diffusion language modeling framework for data-efficient training for the BabyLM 2025 Challenge. Our approach applies diffusion training objectives to language modeling under strict data constraints, incorporating frequency-informed masking that prioritizes learning from rare tokens while maintaining theoretical validity. We explore multiple noise scheduling strategies, including two-mode approaches, and investigate different noise weighting schemes within the NELBO objective. We evaluate our method on the BabyLM benchmark suite, measuring linguistic competence, world knowl"},"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":"2509.05056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T12:35:06Z","cross_cats_sorted":[],"title_canon_sha256":"45c12f3c65bfdd0887e7e7e9e2e0a9bb525f281d2d7c1549e4468e834e4566b3","abstract_canon_sha256":"7928363929c4d32aed0a7e183f030138c8879634c4b2ce166f62cc639382e377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:35.190465Z","signature_b64":"ysb/ANZhmN3mVKC5BkT1Y/O2tZrAVW41AOmtBghPI9z+CgS8VQfQK8okY/sGf7AvQok6pvkBMPuNb0yRUvYgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84167345a10333605f02c4086511199f7fa274edef9bd191b51bc5d58c555b4a","last_reissued_at":"2026-07-05T12:05:35.189855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:35.189855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Diffusion Language Models with Frequency-Informed Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandros Potamianos, Despoina Kosmopoulou, Efthymios Georgiou, Georgios Paraskevopoulos, Vaggelis Dorovatas","submitted_at":"2025-09-05T12:35:06Z","abstract_excerpt":"We present a masked diffusion language modeling framework for data-efficient training for the BabyLM 2025 Challenge. Our approach applies diffusion training objectives to language modeling under strict data constraints, incorporating frequency-informed masking that prioritizes learning from rare tokens while maintaining theoretical validity. We explore multiple noise scheduling strategies, including two-mode approaches, and investigate different noise weighting schemes within the NELBO objective. We evaluate our method on the BabyLM benchmark suite, measuring linguistic competence, world knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05056","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/2509.05056/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":"2509.05056","created_at":"2026-07-05T12:05:35.189926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05056v1","created_at":"2026-07-05T12:05:35.189926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05056","created_at":"2026-07-05T12:05:35.189926+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQLHGRNBAMZW","created_at":"2026-07-05T12:05:35.189926+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQLHGRNBAMZWAXYC","created_at":"2026-07-05T12:05:35.189926+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQLHGRNB","created_at":"2026-07-05T12:05:35.189926+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/QQLHGRNBAMZWAXYCYQEGKEIZT5","json":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5.json","graph_json":"https://pith.science/api/pith-number/QQLHGRNBAMZWAXYCYQEGKEIZT5/graph.json","events_json":"https://pith.science/api/pith-number/QQLHGRNBAMZWAXYCYQEGKEIZT5/events.json","paper":"https://pith.science/paper/QQLHGRNB"},"agent_actions":{"view_html":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5","download_json":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5.json","view_paper":"https://pith.science/paper/QQLHGRNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05056&json=true","fetch_graph":"https://pith.science/api/pith-number/QQLHGRNBAMZWAXYCYQEGKEIZT5/graph.json","fetch_events":"https://pith.science/api/pith-number/QQLHGRNBAMZWAXYCYQEGKEIZT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5/action/storage_attestation","attest_author":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5/action/author_attestation","sign_citation":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5/action/citation_signature","submit_replication":"https://pith.science/pith/QQLHGRNBAMZWAXYCYQEGKEIZT5/action/replication_record"}},"created_at":"2026-07-05T12:05:35.189926+00:00","updated_at":"2026-07-05T12:05:35.189926+00:00"}