{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IQ2BHWN2TXK2VSB74A3FX6OQPJ","short_pith_number":"pith:IQ2BHWN2","schema_version":"1.0","canonical_sha256":"443413d9ba9dd5aac83fe0365bf9d07a440aeb34955c68a7b0b271f7e2b10983","source":{"kind":"arxiv","id":"2605.31268","version":1},"attestation_state":"computed","paper":{"title":"Mellum2 Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aral de Moor, Ivan Bondyrev, Ivan Dolgov, Joseph Shtok, Kseniia Lysaniuk, Madeeswaran Kannan, Marko Kojic, Nikita Pavlichenko, Petr Borovlev","submitted_at":"2026-05-29T13:01:11Z","abstract_excerpt":"We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-purpose language model specialized in software engineering, spanning code generation and editing, debugging, multi-step reasoning, tool use and function calling, agentic coding, and conversational programming assistance, and it is the successor to the completion-focused 4B dense Mellum model. The architecture builds on the Mixture-of-Experts (64 experts, 8 active) and combines Grouped-Query Attention with 4 KV heads, Sliding Window Attention on "},"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":"2605.31268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T13:01:11Z","cross_cats_sorted":[],"title_canon_sha256":"3e2eba258d8b01d282ae3d378a20c4d94cc981b7efd5353b7a416774c11cf358","abstract_canon_sha256":"701986ef2a4c80d4b33eb22c4fb4efe1b2f3a83ec810b307443a49665dcf16f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:07.855854Z","signature_b64":"gC1fI0h+Qvap85I1MNPsmmNiPAeYOU7MvrJB+fLN5f4D5XNyaTwMW59ZL8ilh6twXtJpzOrOKQ3EOe2UkSvBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"443413d9ba9dd5aac83fe0365bf9d07a440aeb34955c68a7b0b271f7e2b10983","last_reissued_at":"2026-06-01T01:04:07.854910Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:07.854910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mellum2 Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aral de Moor, Ivan Bondyrev, Ivan Dolgov, Joseph Shtok, Kseniia Lysaniuk, Madeeswaran Kannan, Marko Kojic, Nikita Pavlichenko, Petr Borovlev","submitted_at":"2026-05-29T13:01:11Z","abstract_excerpt":"We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-purpose language model specialized in software engineering, spanning code generation and editing, debugging, multi-step reasoning, tool use and function calling, agentic coding, and conversational programming assistance, and it is the successor to the completion-focused 4B dense Mellum model. The architecture builds on the Mixture-of-Experts (64 experts, 8 active) and combines Grouped-Query Attention with 4 KV heads, Sliding Window Attention on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31268","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/2605.31268/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":"2605.31268","created_at":"2026-06-01T01:04:07.855076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31268v1","created_at":"2026-06-01T01:04:07.855076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31268","created_at":"2026-06-01T01:04:07.855076+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQ2BHWN2TXK2","created_at":"2026-06-01T01:04:07.855076+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQ2BHWN2TXK2VSB7","created_at":"2026-06-01T01:04:07.855076+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQ2BHWN2","created_at":"2026-06-01T01:04:07.855076+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/IQ2BHWN2TXK2VSB74A3FX6OQPJ","json":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ.json","graph_json":"https://pith.science/api/pith-number/IQ2BHWN2TXK2VSB74A3FX6OQPJ/graph.json","events_json":"https://pith.science/api/pith-number/IQ2BHWN2TXK2VSB74A3FX6OQPJ/events.json","paper":"https://pith.science/paper/IQ2BHWN2"},"agent_actions":{"view_html":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ","download_json":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ.json","view_paper":"https://pith.science/paper/IQ2BHWN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31268&json=true","fetch_graph":"https://pith.science/api/pith-number/IQ2BHWN2TXK2VSB74A3FX6OQPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IQ2BHWN2TXK2VSB74A3FX6OQPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ/action/storage_attestation","attest_author":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ/action/author_attestation","sign_citation":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ/action/citation_signature","submit_replication":"https://pith.science/pith/IQ2BHWN2TXK2VSB74A3FX6OQPJ/action/replication_record"}},"created_at":"2026-06-01T01:04:07.855076+00:00","updated_at":"2026-06-01T01:04:07.855076+00:00"}