{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VDB27S7MI36EBI7OW6ZRD6ZQOV","short_pith_number":"pith:VDB27S7M","canonical_record":{"source":{"id":"2309.12307","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T17:59:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fe2b7082b56abf044c4c8377a65bb43fb7d0a0243f45056042a972a8c2f9cb21","abstract_canon_sha256":"708f04975de8ed6c8ccef528b2dc1aeead5847d61a4aafe60c245a7470241e70"},"schema_version":"1.0"},"canonical_sha256":"a8c3afcbec46fc40a3eeb7b311fb30756afec435af5388f69c4b463bd2161422","source":{"kind":"arxiv","id":"2309.12307","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12307","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12307v3","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12307","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"VDB27S7MI36E","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"VDB27S7MI36EBI7O","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"VDB27S7M","created_at":"2026-07-05T07:53:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VDB27S7MI36EBI7OW6ZRD6ZQOV","target":"record","payload":{"canonical_record":{"source":{"id":"2309.12307","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T17:59:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fe2b7082b56abf044c4c8377a65bb43fb7d0a0243f45056042a972a8c2f9cb21","abstract_canon_sha256":"708f04975de8ed6c8ccef528b2dc1aeead5847d61a4aafe60c245a7470241e70"},"schema_version":"1.0"},"canonical_sha256":"a8c3afcbec46fc40a3eeb7b311fb30756afec435af5388f69c4b463bd2161422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:47.933619Z","signature_b64":"dlVlrmaIQ3Yu5jVwMj6U/N6o2CmisoZoxouyJUrNYVKgUCuDsy/ebO+RjwcXWOWLmBwAkHtSguYaVr0vRkpODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8c3afcbec46fc40a3eeb7b311fb30756afec435af5388f69c4b463bd2161422","last_reissued_at":"2026-07-05T07:53:47.933162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:47.933162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.12307","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0i4pZLk8RS/oudWPTYONlPFVrhh1hEZgPHExGKITBhaLT+Mj0kq4P5P7F0FoJ5btJGmcWWw4HTVhfHb1lpsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:52:26.872334Z"},"content_sha256":"9427f7ac06c9b855158e73cf82b85f5ee604577701ff046c04f26c42f49f3da5","schema_version":"1.0","event_id":"sha256:9427f7ac06c9b855158e73cf82b85f5ee604577701ff046c04f26c42f49f3da5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VDB27S7MI36EBI7OW6ZRD6ZQOV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haotian Tang, Jiaya Jia, Shengju Qian, Song Han, Xin Lai, Yukang Chen, Zhijian Liu","submitted_at":"2023-09-21T17:59:11Z","abstract_excerpt":"We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources. For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048. In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12307","kind":"arxiv","version":3},"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/2309.12307/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":"2026-07-05T07:53:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kKDXWvhHQSOLrwy2MOipYEnlJbk08TO6wfX8+sRbbGnAUFdHlYZ4OzoFYJ7+mxUpZgx8lXvDtcP2dm8b0C4tAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:52:26.873247Z"},"content_sha256":"cb4268f61c84e0635b75459f7dbfb905f5d492fefdecd1903d4eb69acf0392bb","schema_version":"1.0","event_id":"sha256:cb4268f61c84e0635b75459f7dbfb905f5d492fefdecd1903d4eb69acf0392bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV/bundle.json","state_url":"https://pith.science/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV/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":"2026-08-18T03:52:26Z","links":{"resolver":"https://pith.science/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV","bundle":"https://pith.science/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV/bundle.json","state":"https://pith.science/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDB27S7MI36EBI7OW6ZRD6ZQOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VDB27S7MI36EBI7OW6ZRD6ZQOV","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":"708f04975de8ed6c8ccef528b2dc1aeead5847d61a4aafe60c245a7470241e70","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T17:59:11Z","title_canon_sha256":"fe2b7082b56abf044c4c8377a65bb43fb7d0a0243f45056042a972a8c2f9cb21"},"schema_version":"1.0","source":{"id":"2309.12307","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12307","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12307v3","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12307","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"VDB27S7MI36E","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"VDB27S7MI36EBI7O","created_at":"2026-07-05T07:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"VDB27S7M","created_at":"2026-07-05T07:53:47Z"}],"graph_snapshots":[{"event_id":"sha256:cb4268f61c84e0635b75459f7dbfb905f5d492fefdecd1903d4eb69acf0392bb","target":"graph","created_at":"2026-07-05T07:53:47Z","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/2309.12307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources. For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048. In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be ef","authors_text":"Haotian Tang, Jiaya Jia, Shengju Qian, Song Han, Xin Lai, Yukang Chen, Zhijian Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T17:59:11Z","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12307","kind":"arxiv","version":3},"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":"sha256:9427f7ac06c9b855158e73cf82b85f5ee604577701ff046c04f26c42f49f3da5","target":"record","created_at":"2026-07-05T07:53:47Z","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":"708f04975de8ed6c8ccef528b2dc1aeead5847d61a4aafe60c245a7470241e70","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T17:59:11Z","title_canon_sha256":"fe2b7082b56abf044c4c8377a65bb43fb7d0a0243f45056042a972a8c2f9cb21"},"schema_version":"1.0","source":{"id":"2309.12307","kind":"arxiv","version":3}},"canonical_sha256":"a8c3afcbec46fc40a3eeb7b311fb30756afec435af5388f69c4b463bd2161422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8c3afcbec46fc40a3eeb7b311fb30756afec435af5388f69c4b463bd2161422","first_computed_at":"2026-07-05T07:53:47.933162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:47.933162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dlVlrmaIQ3Yu5jVwMj6U/N6o2CmisoZoxouyJUrNYVKgUCuDsy/ebO+RjwcXWOWLmBwAkHtSguYaVr0vRkpODA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:47.933619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12307","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9427f7ac06c9b855158e73cf82b85f5ee604577701ff046c04f26c42f49f3da5","sha256:cb4268f61c84e0635b75459f7dbfb905f5d492fefdecd1903d4eb69acf0392bb"],"state_sha256":"d5ab81edbde06d430b19b27e6323c63686b259ff0e57f0a35e5983e9256d2837"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XDo08sKiolxK3NrHw+0dCwmPzKaYxoSTqhYzL+8IqjAhjjIIaLZlqy6KenjiwI+9t7KWzZz5c/iFNTLpQWAiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:52:26.880834Z","bundle_sha256":"d3e3fcda9729267a09ec05952d6392707a8c481d6971a8f10fc308856559f60b"}}