{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R2TBN5BFRPWHCCGJSVE2IAA6PC","short_pith_number":"pith:R2TBN5BF","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"},"canonical_sha256":"8ea616f4258bec7108c99549a4001e78a67937d433b6b3a7d83823ad9570521e","source":{"kind":"arxiv","id":"2608.05141","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05141","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05141v1","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05141","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"R2TBN5BFRPWH","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"pith_short_16","alias_value":"R2TBN5BFRPWHCCGJ","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"pith_short_8","alias_value":"R2TBN5BF","created_at":"2026-08-06T01:49:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R2TBN5BFRPWHCCGJSVE2IAA6PC","target":"record","payload":{"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"},"canonical_sha256":"8ea616f4258bec7108c99549a4001e78a67937d433b6b3a7d83823ad9570521e","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"},"source_kind":"arxiv","source_id":"2608.05141","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:49:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"goWM4XhJgcPlv0r0CQ9sq8Gtcu1AOQXAH7iPg37lt4W78lV3ei+nngtGL2+KQx2rYsspOQXKkp7URSuHE5ANAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:25:46.238837Z"},"content_sha256":"289dabc1820cf4f4a0caeabf6bcac69c24fc3b2f4fb82b65e1e8a43f162c1c79","schema_version":"1.0","event_id":"sha256:289dabc1820cf4f4a0caeabf6bcac69c24fc3b2f4fb82b65e1e8a43f162c1c79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R2TBN5BFRPWHCCGJSVE2IAA6PC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:49:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DkjOxVeJtVOEbaAN0qdyq2HNgHCt8ojwQLapRzyVvueMYfWRRfLmD/py4KR5GYSkCGAZml4QdkCD5DVvqR6MDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:25:46.239553Z"},"content_sha256":"2e0d3126337e5fbe4ae2dcdfd2a908071374cc2a415f7ce481f4d64634900c9f","schema_version":"1.0","event_id":"sha256:2e0d3126337e5fbe4ae2dcdfd2a908071374cc2a415f7ce481f4d64634900c9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/bundle.json","state_url":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T19:25:46Z","links":{"resolver":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC","bundle":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/bundle.json","state":"https://pith.science/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2TBN5BFRPWHCCGJSVE2IAA6PC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R2TBN5BFRPWHCCGJSVE2IAA6PC","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":"9009ff0e4958e1b88e1b800284a3adab991833f40139c4076d6f1b03423e05ef","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:58:15Z","title_canon_sha256":"a7f7d46607bad7aa117cc9faab399bc37106dd8314a702ecfd0058ed6cd98f14"},"schema_version":"1.0","source":{"id":"2608.05141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05141","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05141v1","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05141","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"R2TBN5BFRPWH","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"pith_short_16","alias_value":"R2TBN5BFRPWHCCGJ","created_at":"2026-08-06T01:49:16Z"},{"alias_kind":"pith_short_8","alias_value":"R2TBN5BF","created_at":"2026-08-06T01:49:16Z"}],"graph_snapshots":[{"event_id":"sha256:2e0d3126337e5fbe4ae2dcdfd2a908071374cc2a415f7ce481f4d64634900c9f","target":"graph","created_at":"2026-08-06T01:49:16Z","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/2608.05141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Falko Helm, Goran Glava\\v{s}, Indraneil Paul, Iryna Gurevych","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:58:15Z","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05141","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":"sha256:289dabc1820cf4f4a0caeabf6bcac69c24fc3b2f4fb82b65e1e8a43f162c1c79","target":"record","created_at":"2026-08-06T01:49:16Z","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":"9009ff0e4958e1b88e1b800284a3adab991833f40139c4076d6f1b03423e05ef","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:58:15Z","title_canon_sha256":"a7f7d46607bad7aa117cc9faab399bc37106dd8314a702ecfd0058ed6cd98f14"},"schema_version":"1.0","source":{"id":"2608.05141","kind":"arxiv","version":1}},"canonical_sha256":"8ea616f4258bec7108c99549a4001e78a67937d433b6b3a7d83823ad9570521e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ea616f4258bec7108c99549a4001e78a67937d433b6b3a7d83823ad9570521e","first_computed_at":"2026-08-06T01:49:16.796472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:49:16.796472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SYNgFUyjgIKmx/VtyZ3wJO+MAEROZ1hMwUF1c+iX//OG4L4bd24IEK4UTKlBT7CngevNyyB5cBsaTaAPs7xzAg==","signature_status":"signed_v1","signed_at":"2026-08-06T01:49:16.797923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:289dabc1820cf4f4a0caeabf6bcac69c24fc3b2f4fb82b65e1e8a43f162c1c79","sha256:2e0d3126337e5fbe4ae2dcdfd2a908071374cc2a415f7ce481f4d64634900c9f"],"state_sha256":"b53f97c6535cd937f4de76edf46600b076518e50af1f383752df8f86fc482b2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9U0xgDO2Zwm7UoCibl262AOuLHcCgf3uTmIEoX0ybhF1fqg3atFFyf77rsBJlIq8WPokCo/HYAE7ZnbUsWI0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:25:46.243877Z","bundle_sha256":"b4bf12367a831524c5fee9e5bbabe5bc2a5e76c2133f01b57ceb3513cab96d8c"}}