{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TL7CGPZQXYIQOHU26FFGNK7LAX","short_pith_number":"pith:TL7CGPZQ","schema_version":"1.0","canonical_sha256":"9afe233f30be11071e9af14a66abeb05d1ecafcc3476a9f53639531908177457","source":{"kind":"arxiv","id":"2608.06758","version":1},"attestation_state":"computed","paper":{"title":"Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Aida, Kosuke Arima, Makoto Morinaga, Shi Chen, Shohei Tanaka","submitted_at":"2026-08-07T03:24:59Z","abstract_excerpt":"We present Stockmark-Nemotron-3-Nano-Omni-JapanDocReader, a Japanese document understanding model built from Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. The central goal of this work is structured document parsing via capability injection and forgetting control: we inject Japanese structured document parsing capability into a reasoning-oriented multimodal model while preserving its document VQA capability as much as possible. We study parsing-centric SFT, which uses only structured document parsing data; mixed SFT, which combines structured document parsing and VQA data; and parsing-centric R"},"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":"2608.06758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T03:24:59Z","cross_cats_sorted":[],"title_canon_sha256":"e72cf0dad0a416db0d8b111130bd194588cf5f5fa35f2bdf6e74694af56c8507","abstract_canon_sha256":"0bed57746ce154d3a8f06fc3f666988056c9556af5eecbc8b951599e16406517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:11:57.221022Z","signature_b64":"xKGkFsfXiGE25ikbsf+h3xEgCp33kDx+O98ZS9A1XuSNouAcRbDUWjPjete00ZU7VzY2ghExe5jI4R5fMvTCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9afe233f30be11071e9af14a66abeb05d1ecafcc3476a9f53639531908177457","last_reissued_at":"2026-08-10T01:11:57.218642Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:11:57.218642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Aida, Kosuke Arima, Makoto Morinaga, Shi Chen, Shohei Tanaka","submitted_at":"2026-08-07T03:24:59Z","abstract_excerpt":"We present Stockmark-Nemotron-3-Nano-Omni-JapanDocReader, a Japanese document understanding model built from Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. The central goal of this work is structured document parsing via capability injection and forgetting control: we inject Japanese structured document parsing capability into a reasoning-oriented multimodal model while preserving its document VQA capability as much as possible. We study parsing-centric SFT, which uses only structured document parsing data; mixed SFT, which combines structured document parsing and VQA data; and parsing-centric R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06758","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/2608.06758/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":"2608.06758","created_at":"2026-08-10T01:11:57.219652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06758v1","created_at":"2026-08-10T01:11:57.219652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06758","created_at":"2026-08-10T01:11:57.219652+00:00"},{"alias_kind":"pith_short_12","alias_value":"TL7CGPZQXYIQ","created_at":"2026-08-10T01:11:57.219652+00:00"},{"alias_kind":"pith_short_16","alias_value":"TL7CGPZQXYIQOHU2","created_at":"2026-08-10T01:11:57.219652+00:00"},{"alias_kind":"pith_short_8","alias_value":"TL7CGPZQ","created_at":"2026-08-10T01:11:57.219652+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/TL7CGPZQXYIQOHU26FFGNK7LAX","json":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX.json","graph_json":"https://pith.science/api/pith-number/TL7CGPZQXYIQOHU26FFGNK7LAX/graph.json","events_json":"https://pith.science/api/pith-number/TL7CGPZQXYIQOHU26FFGNK7LAX/events.json","paper":"https://pith.science/paper/TL7CGPZQ"},"agent_actions":{"view_html":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX","download_json":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX.json","view_paper":"https://pith.science/paper/TL7CGPZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06758&json=true","fetch_graph":"https://pith.science/api/pith-number/TL7CGPZQXYIQOHU26FFGNK7LAX/graph.json","fetch_events":"https://pith.science/api/pith-number/TL7CGPZQXYIQOHU26FFGNK7LAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX/action/storage_attestation","attest_author":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX/action/author_attestation","sign_citation":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX/action/citation_signature","submit_replication":"https://pith.science/pith/TL7CGPZQXYIQOHU26FFGNK7LAX/action/replication_record"}},"created_at":"2026-08-10T01:11:57.219652+00:00","updated_at":"2026-08-10T01:11:57.219652+00:00"}