{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H736W5G27HVEHKOZF4GMWHBQVI","short_pith_number":"pith:H736W5G2","canonical_record":{"source":{"id":"2405.17915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T07:36:56Z","cross_cats_sorted":[],"title_canon_sha256":"15a17fac638772fca2907c09addee2135f22ff90210d4ae528a1b168b9668cfb","abstract_canon_sha256":"368653c55ff6d90e0a8458e5b68a04e77781a70136be5b6a7e4a3078bb22c6bb"},"schema_version":"1.0"},"canonical_sha256":"3ff7eb74daf9ea43a9d92f0ccb1c30aa38c90c75a334c2fc5350bcec5eb5f675","source":{"kind":"arxiv","id":"2405.17915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17915","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17915v1","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17915","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"H736W5G27HVE","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"H736W5G27HVEHKOZ","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"H736W5G2","created_at":"2026-07-05T08:24:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H736W5G27HVEHKOZF4GMWHBQVI","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T07:36:56Z","cross_cats_sorted":[],"title_canon_sha256":"15a17fac638772fca2907c09addee2135f22ff90210d4ae528a1b168b9668cfb","abstract_canon_sha256":"368653c55ff6d90e0a8458e5b68a04e77781a70136be5b6a7e4a3078bb22c6bb"},"schema_version":"1.0"},"canonical_sha256":"3ff7eb74daf9ea43a9d92f0ccb1c30aa38c90c75a334c2fc5350bcec5eb5f675","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:12.968184Z","signature_b64":"csdPUQwkIxmNBVXTzPK10ekgLqnqU/1Tkf03OH/AW9feLbDy7VxiuNmgNZRGaYVeo8VdQERdHJ31Wfjg75xICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ff7eb74daf9ea43a9d92f0ccb1c30aa38c90c75a334c2fc5350bcec5eb5f675","last_reissued_at":"2026-07-05T08:24:12.967758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:12.967758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17915","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":"2026-07-05T08:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGWJNYqWX75i7/xI4Y/SFkSFc5W0WYYfeFNpdhpP9vqCBB8pvNJnNcTzvRcRXlVM6P2zcf98CLAtGZ+tHvH+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:58:23.395908Z"},"content_sha256":"7d90ef0d0f060e67c256a372bf1f28b082fe61c283a6761ab409f45dc9d434ba","schema_version":"1.0","event_id":"sha256:7d90ef0d0f060e67c256a372bf1f28b082fe61c283a6761ab409f45dc9d434ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H736W5G27HVEHKOZF4GMWHBQVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Longze Chen, Min Yang, Run Luo, Wanwei He, Yunshui Li, Ziqiang Liu","submitted_at":"2024-05-28T07:36:56Z","abstract_excerpt":"Long-context modeling capabilities are important for large language models (LLMs) in various applications. However, directly training LLMs with long context windows is insufficient to enhance this capability since some training samples do not exhibit strong semantic dependencies across long contexts. In this study, we propose a data mining framework \\textbf{ProLong} that can assign each training sample with a long dependency score, which can be used to rank and filter samples that are more advantageous for enhancing long-context modeling abilities in LLM training. Specifically, we first use de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17915","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/2405.17915/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":"2026-07-05T08:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1c3ima0eBvHow5RYVL3y9dG+UedAPB+AhdntcOrtjb0P6tDV4HCqx0ioj9j+CczOitNegC5bdcbIGPurBWmNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:58:23.396414Z"},"content_sha256":"a267e8f30c8cb08084978ac7b2f8307918486c1f20fadc255ac4b482fe4a0c1f","schema_version":"1.0","event_id":"sha256:a267e8f30c8cb08084978ac7b2f8307918486c1f20fadc255ac4b482fe4a0c1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H736W5G27HVEHKOZF4GMWHBQVI/bundle.json","state_url":"https://pith.science/pith/H736W5G27HVEHKOZF4GMWHBQVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H736W5G27HVEHKOZF4GMWHBQVI/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":"2026-08-21T16:58:23Z","links":{"resolver":"https://pith.science/pith/H736W5G27HVEHKOZF4GMWHBQVI","bundle":"https://pith.science/pith/H736W5G27HVEHKOZF4GMWHBQVI/bundle.json","state":"https://pith.science/pith/H736W5G27HVEHKOZF4GMWHBQVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H736W5G27HVEHKOZF4GMWHBQVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H736W5G27HVEHKOZF4GMWHBQVI","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":"368653c55ff6d90e0a8458e5b68a04e77781a70136be5b6a7e4a3078bb22c6bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T07:36:56Z","title_canon_sha256":"15a17fac638772fca2907c09addee2135f22ff90210d4ae528a1b168b9668cfb"},"schema_version":"1.0","source":{"id":"2405.17915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17915","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17915v1","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17915","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"H736W5G27HVE","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"H736W5G27HVEHKOZ","created_at":"2026-07-05T08:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"H736W5G2","created_at":"2026-07-05T08:24:12Z"}],"graph_snapshots":[{"event_id":"sha256:a267e8f30c8cb08084978ac7b2f8307918486c1f20fadc255ac4b482fe4a0c1f","target":"graph","created_at":"2026-07-05T08:24:12Z","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/2405.17915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-context modeling capabilities are important for large language models (LLMs) in various applications. However, directly training LLMs with long context windows is insufficient to enhance this capability since some training samples do not exhibit strong semantic dependencies across long contexts. In this study, we propose a data mining framework \\textbf{ProLong} that can assign each training sample with a long dependency score, which can be used to rank and filter samples that are more advantageous for enhancing long-context modeling abilities in LLM training. Specifically, we first use de","authors_text":"Longze Chen, Min Yang, Run Luo, Wanwei He, Yunshui Li, Ziqiang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T07:36:56Z","title":"Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17915","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":"sha256:7d90ef0d0f060e67c256a372bf1f28b082fe61c283a6761ab409f45dc9d434ba","target":"record","created_at":"2026-07-05T08:24:12Z","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":"368653c55ff6d90e0a8458e5b68a04e77781a70136be5b6a7e4a3078bb22c6bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T07:36:56Z","title_canon_sha256":"15a17fac638772fca2907c09addee2135f22ff90210d4ae528a1b168b9668cfb"},"schema_version":"1.0","source":{"id":"2405.17915","kind":"arxiv","version":1}},"canonical_sha256":"3ff7eb74daf9ea43a9d92f0ccb1c30aa38c90c75a334c2fc5350bcec5eb5f675","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ff7eb74daf9ea43a9d92f0ccb1c30aa38c90c75a334c2fc5350bcec5eb5f675","first_computed_at":"2026-07-05T08:24:12.967758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:12.967758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"csdPUQwkIxmNBVXTzPK10ekgLqnqU/1Tkf03OH/AW9feLbDy7VxiuNmgNZRGaYVeo8VdQERdHJ31Wfjg75xICA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:12.968184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d90ef0d0f060e67c256a372bf1f28b082fe61c283a6761ab409f45dc9d434ba","sha256:a267e8f30c8cb08084978ac7b2f8307918486c1f20fadc255ac4b482fe4a0c1f"],"state_sha256":"825a9ec4fc4485c53c191aa643be256d067fb1fcf8f4c380cf30532e0d39b75a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3v+YMRzyNFQ4mu7NkEUgGzdsv6QL4davVDpm2/LhQbdfjhrpNWgRTRJbia8JGS3B7NCrd1xmjSlQ3xk59ZeDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T16:58:23.401669Z","bundle_sha256":"316b06772157e6297edb1ddcebc59c7dcf4f3f01118cad80c1a23f2b4e06a3d6"}}