{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VWA7FD7ARCWQZSK3W4T7PKZSPJ","short_pith_number":"pith:VWA7FD7A","canonical_record":{"source":{"id":"2406.00605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T03:34:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b9583a4f6300c22101ce9f68ee3e34d89ea7ccb53356595e56251dc2688194a","abstract_canon_sha256":"59432d7c41cb558b3f6b6622d10e3b554b11c694ec93f7313123f0a2e3c894e8"},"schema_version":"1.0"},"canonical_sha256":"ad81f28fe088ad0cc95bb727f7ab327a57a72ebb961d99bdfd1fb7fb2ff01e16","source":{"kind":"arxiv","id":"2406.00605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00605","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00605v1","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00605","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"VWA7FD7ARCWQ","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"VWA7FD7ARCWQZSK3","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"VWA7FD7A","created_at":"2026-07-05T08:26:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VWA7FD7ARCWQZSK3W4T7PKZSPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T03:34:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b9583a4f6300c22101ce9f68ee3e34d89ea7ccb53356595e56251dc2688194a","abstract_canon_sha256":"59432d7c41cb558b3f6b6622d10e3b554b11c694ec93f7313123f0a2e3c894e8"},"schema_version":"1.0"},"canonical_sha256":"ad81f28fe088ad0cc95bb727f7ab327a57a72ebb961d99bdfd1fb7fb2ff01e16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:27.995926Z","signature_b64":"i+XBjonCo3uoOhtwvZaMf32AG//IKeJjouWg5RVH+mySdcnrLkQNps8GzthmIzP5WPvuk3W30SQpSyS34v2pCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad81f28fe088ad0cc95bb727f7ab327a57a72ebb961d99bdfd1fb7fb2ff01e16","last_reissued_at":"2026-07-05T08:26:27.995414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:27.995414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00605","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":"2026-07-05T08:26:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0G36SYkuV0zk5QBrWg56Wp23wf98qXh/Y22v73vGh+arfFG5AZOxR0B3C45uo1uEMyiPFFfpMNc+xPhe+hbEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:11:41.491155Z"},"content_sha256":"657054e3e120e107a9f298566ec27e80ecbde47c725ac305c623ad4c612b76a8","schema_version":"1.0","event_id":"sha256:657054e3e120e107a9f298566ec27e80ecbde47c725ac305c623ad4c612b76a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VWA7FD7ARCWQZSK3W4T7PKZSPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Zhu, Cheng cheng, Chenxia Li, Han Fang, Liang Zeng, Liang Zhao, Lijie Wang, Liu Yang, Peng Cheng, Rui Hu, Shuicheng Yan, Tianwen Wei, Xuejie Wu, Yahui Zhou, Yimeng Gan","submitted_at":"2024-06-02T03:34:41Z","abstract_excerpt":"We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200,000 tokens. We provide a training recipe for efficiently extending context length of LLMs. We identify that the critical element in enhancing long-context processing capability is to incorporate a long-context SFT stage following the standard SFT stage. A mere 200 iterations can convert the standard SFT model into a long-context model. To reduce the effort in collecting and annotating data for long-context language modeling, we develop two novel methods for creating synthetic data. These methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00605","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/2406.00605/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":"2026-07-05T08:26:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m90Yz/YRrFOcthND3eXmDbquI2fxf7TvM6HL2bqQdrMUrN6by4kvAlsiCVoqYWMtKibJRUM7Da+th+VpKwx5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:11:41.491559Z"},"content_sha256":"b977658c465a2869fbbc27782ab23aa680d28d08c8eaf452aa78fba2cbdaf1c8","schema_version":"1.0","event_id":"sha256:b977658c465a2869fbbc27782ab23aa680d28d08c8eaf452aa78fba2cbdaf1c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ/bundle.json","state_url":"https://pith.science/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ/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":"2026-07-07T04:11:41Z","links":{"resolver":"https://pith.science/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ","bundle":"https://pith.science/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ/bundle.json","state":"https://pith.science/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWA7FD7ARCWQZSK3W4T7PKZSPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VWA7FD7ARCWQZSK3W4T7PKZSPJ","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":"59432d7c41cb558b3f6b6622d10e3b554b11c694ec93f7313123f0a2e3c894e8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T03:34:41Z","title_canon_sha256":"1b9583a4f6300c22101ce9f68ee3e34d89ea7ccb53356595e56251dc2688194a"},"schema_version":"1.0","source":{"id":"2406.00605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00605","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00605v1","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00605","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"VWA7FD7ARCWQ","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"VWA7FD7ARCWQZSK3","created_at":"2026-07-05T08:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"VWA7FD7A","created_at":"2026-07-05T08:26:27Z"}],"graph_snapshots":[{"event_id":"sha256:b977658c465a2869fbbc27782ab23aa680d28d08c8eaf452aa78fba2cbdaf1c8","target":"graph","created_at":"2026-07-05T08:26:27Z","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/2406.00605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200,000 tokens. We provide a training recipe for efficiently extending context length of LLMs. We identify that the critical element in enhancing long-context processing capability is to incorporate a long-context SFT stage following the standard SFT stage. A mere 200 iterations can convert the standard SFT model into a long-context model. To reduce the effort in collecting and annotating data for long-context language modeling, we develop two novel methods for creating synthetic data. These methods","authors_text":"Bo Zhu, Cheng cheng, Chenxia Li, Han Fang, Liang Zeng, Liang Zhao, Lijie Wang, Liu Yang, Peng Cheng, Rui Hu, Shuicheng Yan, Tianwen Wei, Xuejie Wu, Yahui Zhou, Yimeng Gan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T03:34:41Z","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00605","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":"sha256:657054e3e120e107a9f298566ec27e80ecbde47c725ac305c623ad4c612b76a8","target":"record","created_at":"2026-07-05T08:26:27Z","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":"59432d7c41cb558b3f6b6622d10e3b554b11c694ec93f7313123f0a2e3c894e8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T03:34:41Z","title_canon_sha256":"1b9583a4f6300c22101ce9f68ee3e34d89ea7ccb53356595e56251dc2688194a"},"schema_version":"1.0","source":{"id":"2406.00605","kind":"arxiv","version":1}},"canonical_sha256":"ad81f28fe088ad0cc95bb727f7ab327a57a72ebb961d99bdfd1fb7fb2ff01e16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad81f28fe088ad0cc95bb727f7ab327a57a72ebb961d99bdfd1fb7fb2ff01e16","first_computed_at":"2026-07-05T08:26:27.995414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:27.995414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+XBjonCo3uoOhtwvZaMf32AG//IKeJjouWg5RVH+mySdcnrLkQNps8GzthmIzP5WPvuk3W30SQpSyS34v2pCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:27.995926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:657054e3e120e107a9f298566ec27e80ecbde47c725ac305c623ad4c612b76a8","sha256:b977658c465a2869fbbc27782ab23aa680d28d08c8eaf452aa78fba2cbdaf1c8"],"state_sha256":"41c765d03800a73c6c13ebbfb8d899302850b6004fbd70fc4e31c9bcc8441c51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"felhGoMI/9HEL4jAl1JhqcZgEnf/hh36QpFBNTLLmOr/QTvGU6pEtqephrUav916L2aFUjyIcDEE0q5ibR5MCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:11:41.493647Z","bundle_sha256":"3cc751f82df903bee9a322f614ed3f177de326c9ab7f70e23607011cba650181"}}