{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QQLHGRNBAMZWAXYCYQEGKEIZT5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7928363929c4d32aed0a7e183f030138c8879634c4b2ce166f62cc639382e377","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T12:35:06Z","title_canon_sha256":"45c12f3c65bfdd0887e7e7e9e2e0a9bb525f281d2d7c1549e4468e834e4566b3"},"schema_version":"1.0","source":{"id":"2509.05056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05056","created_at":"2026-07-05T12:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05056v1","created_at":"2026-07-05T12:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05056","created_at":"2026-07-05T12:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"QQLHGRNBAMZW","created_at":"2026-07-05T12:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"QQLHGRNBAMZWAXYC","created_at":"2026-07-05T12:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"QQLHGRNB","created_at":"2026-07-05T12:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:7b65c499652625c27a74df9416fec10712b2adbad3ee700f918cd850ffd163d7","target":"graph","created_at":"2026-07-05T12:05:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.05056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexandros Potamianos, Despoina Kosmopoulou, Efthymios Georgiou, Georgios Paraskevopoulos, Vaggelis Dorovatas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T12:35:06Z","title":"Masked Diffusion Language Models with Frequency-Informed Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05056","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:41d7751a891964871d004b4eb9ca01b1fed93a2c202fc6a09c6092fccad6f15f","target":"record","created_at":"2026-07-05T12:05:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7928363929c4d32aed0a7e183f030138c8879634c4b2ce166f62cc639382e377","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T12:35:06Z","title_canon_sha256":"45c12f3c65bfdd0887e7e7e9e2e0a9bb525f281d2d7c1549e4468e834e4566b3"},"schema_version":"1.0","source":{"id":"2509.05056","kind":"arxiv","version":1}},"canonical_sha256":"84167345a10333605f02c4086511199f7fa274edef9bd191b51bc5d58c555b4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84167345a10333605f02c4086511199f7fa274edef9bd191b51bc5d58c555b4a","first_computed_at":"2026-07-05T12:05:35.189855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:35.189855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysb/ANZhmN3mVKC5BkT1Y/O2tZrAVW41AOmtBghPI9z+CgS8VQfQK8okY/sGf7AvQok6pvkBMPuNb0yRUvYgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:35.190465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d7751a891964871d004b4eb9ca01b1fed93a2c202fc6a09c6092fccad6f15f","sha256:7b65c499652625c27a74df9416fec10712b2adbad3ee700f918cd850ffd163d7"],"state_sha256":"ca5e0c13b0b2ff854e43825c9575774ea157d65bad2f0033a2ca68ece92e0e0d"}