{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R2TBN5BFRPWHCCGJSVE2IAA6PC","short_pith_number":"pith:R2TBN5BF","schema_version":"1.0","canonical_sha256":"8ea616f4258bec7108c99549a4001e78a67937d433b6b3a7d83823ad9570521e","source":{"kind":"arxiv","id":"2608.05141","version":1},"attestation_state":"computed","paper":{"title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Falko Helm, Goran Glava\\v{s}, Indraneil Paul, Iryna Gurevych","submitted_at":"2026-08-05T17:58:15Z","abstract_excerpt":"Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies. In this work, we introduce OctoLong, a context engineering pipeline that instruments an AST parser, a language server backend, and a package manager to facilitate the recursive retrieval of code references, enabling the curation of dependency-rich "},"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":"2608.05141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:58:15Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"a7f7d46607bad7aa117cc9faab399bc37106dd8314a702ecfd0058ed6cd98f14","abstract_canon_sha256":"9009ff0e4958e1b88e1b800284a3adab991833f40139c4076d6f1b03423e05ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:49:16.797923Z","signature_b64":"SYNgFUyjgIKmx/VtyZ3wJO+MAEROZ1hMwUF1c+iX//OG4L4bd24IEK4UTKlBT7CngevNyyB5cBsaTaAPs7xzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ea616f4258bec7108c99549a4001e78a67937d433b6b3a7d83823ad9570521e","last_reissued_at":"2026-08-06T01:49:16.796472Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:49:16.796472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Falko Helm, Goran Glava\\v{s}, Indraneil Paul, Iryna Gurevych","submitted_at":"2026-08-05T17:58:15Z","abstract_excerpt":"Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies. In this work, we introduce OctoLong, a context engineering pipeline that instruments an AST parser, a language server backend, and a package manager to facilitate the recursive retrieval of code references, enabling the curation of dependency-rich "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05141","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/2608.05141/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":"2608.05141","created_at":"2026-08-06T01:49:16.798339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05141v1","created_at":"2026-08-06T01:49:16.798339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05141","created_at":"2026-08-06T01:49:16.798339+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2TBN5BFRPWH","created_at":"2026-08-06T01:49:16.798339+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2TBN5BFRPWHCCGJ","created_at":"2026-08-06T01:49:16.798339+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2TBN5BF","created_at":"2026-08-06T01:49:16.798339+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/R2TBN5BFRPWHCCGJSVE2IAA6PC","json":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC.json","graph_json":"https://pith.science/api/pith-number/R2TBN5BFRPWHCCGJSVE2IAA6PC/graph.json","events_json":"https://pith.science/api/pith-number/R2TBN5BFRPWHCCGJSVE2IAA6PC/events.json","paper":"https://pith.science/paper/R2TBN5BF"},"agent_actions":{"view_html":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC","download_json":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC.json","view_paper":"https://pith.science/paper/R2TBN5BF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05141&json=true","fetch_graph":"https://pith.science/api/pith-number/R2TBN5BFRPWHCCGJSVE2IAA6PC/graph.json","fetch_events":"https://pith.science/api/pith-number/R2TBN5BFRPWHCCGJSVE2IAA6PC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/action/storage_attestation","attest_author":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/action/author_attestation","sign_citation":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/action/citation_signature","submit_replication":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/action/replication_record"}},"created_at":"2026-08-06T01:49:16.798339+00:00","updated_at":"2026-08-06T01:49:16.798339+00:00"}