{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HGNUMGCMGAKCUNNONMRSIDPLRT","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":"01f4b72751d433f8d6b040f9647bfa35bb8c71bc509e508ecc78303b0830016b","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:35:47Z","title_canon_sha256":"ac6b88c202a069653febaeaab925ac846bfc21f91b2f993dacd3f4f06f28863a"},"schema_version":"1.0","source":{"id":"2407.14482","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14482","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14482v3","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14482","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"HGNUMGCMGAKC","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"HGNUMGCMGAKCUNNO","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"HGNUMGCM","created_at":"2026-07-05T10:14:43Z"}],"graph_snapshots":[{"event_id":"sha256:e518960778bc39923dae1092b0b6291288808485cbec245a55c1bd4446c7b784","target":"graph","created_at":"2026-07-05T10:14:43Z","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/2407.14482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce ChatQA 2, an Llama 3.0-based model with a 128K context window, designed to bridge the gap between open-source LLMs and leading proprietary models (e.g., GPT-4-Turbo-2024-04-09) in long context understanding and retrieval-augmented generation (RAG) capabilities. These two capabilities are complementary to each other and essential for LLMs to process large volumes of information that cannot fit into a single prompt. We present a detailed continued training recipe to extend the context window of Llama3-70B-base from 8K to 128K tokens, along with a three-stage instructio","authors_text":"Bryan Catanzaro, Chejian Xu, Mohammad Shoeybi, Peng Xu, Wei Ping, Xianchao Wu, Zihan Liu","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:35:47Z","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14482","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":"sha256:3654aa6a9b25933d4f03cb77d1dc582d060cc60697db27e73982129414ac0781","target":"record","created_at":"2026-07-05T10:14:43Z","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":"01f4b72751d433f8d6b040f9647bfa35bb8c71bc509e508ecc78303b0830016b","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:35:47Z","title_canon_sha256":"ac6b88c202a069653febaeaab925ac846bfc21f91b2f993dacd3f4f06f28863a"},"schema_version":"1.0","source":{"id":"2407.14482","kind":"arxiv","version":3}},"canonical_sha256":"399b46184c30142a35ae6b23240deb8cd99427a214e9f43522a80495dbdb9e05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"399b46184c30142a35ae6b23240deb8cd99427a214e9f43522a80495dbdb9e05","first_computed_at":"2026-07-05T10:14:43.667948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:43.667948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6w8qX3cnyjbj3rzVwgB6yeG0KYEWmcU7XHoqrO6RdWQc+4uXxxYckQg4XdxIi79y2hX6XP8dqXquaItBZFQUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:43.668480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14482","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3654aa6a9b25933d4f03cb77d1dc582d060cc60697db27e73982129414ac0781","sha256:e518960778bc39923dae1092b0b6291288808485cbec245a55c1bd4446c7b784"],"state_sha256":"d5bf1c19f219ac9b30120900298c8b9f4133613a9b6d14efc97e40b4de243482"}