{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RWJM7VDI4FLCQLMDAIPST4FOHQ","short_pith_number":"pith:RWJM7VDI","canonical_record":{"source":{"id":"2309.03450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-07T02:20:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cc01df77d3a1bbd1302852e5af08a75e767fafbf0e1abf2feda00d573bd08ceb","abstract_canon_sha256":"4e1a040fca84e871105dab14ec04dbb96ba914a94f297cf457de1b116e33c2af"},"schema_version":"1.0"},"canonical_sha256":"8d92cfd468e156282d83021f29f0ae3c39987c6b59a9c06a82c5b3850a95d253","source":{"kind":"arxiv","id":"2309.03450","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03450","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03450v1","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03450","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"pith_short_12","alias_value":"RWJM7VDI4FLC","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"pith_short_16","alias_value":"RWJM7VDI4FLCQLMD","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"pith_short_8","alias_value":"RWJM7VDI","created_at":"2026-07-05T06:48:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RWJM7VDI4FLCQLMDAIPST4FOHQ","target":"record","payload":{"canonical_record":{"source":{"id":"2309.03450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-07T02:20:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cc01df77d3a1bbd1302852e5af08a75e767fafbf0e1abf2feda00d573bd08ceb","abstract_canon_sha256":"4e1a040fca84e871105dab14ec04dbb96ba914a94f297cf457de1b116e33c2af"},"schema_version":"1.0"},"canonical_sha256":"8d92cfd468e156282d83021f29f0ae3c39987c6b59a9c06a82c5b3850a95d253","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:28.439345Z","signature_b64":"nQ368Amb6F8n9gs6p1cH2Uns+Pn6xIbta2RJWEomVfaqwxmF4bs6YRg9uCJ3bKxPDnLmAvbKswMkFqy51+NeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d92cfd468e156282d83021f29f0ae3c39987c6b59a9c06a82c5b3850a95d253","last_reissued_at":"2026-07-05T06:48:28.438865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:28.438865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.03450","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":"2026-07-05T06:48:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/+eA77p7C3BaPZ5ieSXuozeO/L1/8kiKPcl6agQQbclFSFTSXxKK69FWFPSfSnI3l7lFos4T8pYvRspTjDKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:12:46.879538Z"},"content_sha256":"596c8ad341592463b0a22e67a747b54ba9e248de5cfa7f53c9dfd7d75f188274","schema_version":"1.0","event_id":"sha256:596c8ad341592463b0a22e67a747b54ba9e248de5cfa7f53c9dfd7d75f188274"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RWJM7VDI4FLCQLMDAIPST4FOHQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XGen-7B Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Fabbri, Ben Krause, Bo Pang, Caiming Xiong, Chen Xing, Chien-Sheng Wu, Congying Xia, Erik Nijkamp, Hiroaki Hayashi, Jesse Vig, Lidiya Murakhovs'ka, Lifu Tu, Meghana Bhat, Philippe Laban, Prafulla Kumar Choubey, Rui Meng, Semih Yavuz, Senthil Purushwalkam, Shafiq Joty, Silvio Savarese, Tian Xie, Tong Niu, Wojciech Kry\\'sci\\'nski, Ye Liu, Yingbo Zhou","submitted_at":"2023-09-07T02:20:03Z","abstract_excerpt":"Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary walls, hindering scientific progress. Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context. To address this, we have trained XGen, a series of 7B parameter models on up to 8K sequence length for up to 1.5T tokens. We have also finetuned the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03450","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/2309.03450/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":"2026-07-05T06:48:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8fJnDo7Vt6g2Z4gvjtRoOYWmyDGTiDctnzw+BToiXp0eBGq1clmku/p49lcaloePgxmX69L54MczlJUhFxSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:12:46.879917Z"},"content_sha256":"9d033b691893d5f87e96e83e43324791c9ea31dc9af4ba05429dc93a7237e531","schema_version":"1.0","event_id":"sha256:9d033b691893d5f87e96e83e43324791c9ea31dc9af4ba05429dc93a7237e531"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ/bundle.json","state_url":"https://pith.science/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ/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":"2026-07-08T23:12:46Z","links":{"resolver":"https://pith.science/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ","bundle":"https://pith.science/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ/bundle.json","state":"https://pith.science/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWJM7VDI4FLCQLMDAIPST4FOHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RWJM7VDI4FLCQLMDAIPST4FOHQ","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":"4e1a040fca84e871105dab14ec04dbb96ba914a94f297cf457de1b116e33c2af","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-07T02:20:03Z","title_canon_sha256":"cc01df77d3a1bbd1302852e5af08a75e767fafbf0e1abf2feda00d573bd08ceb"},"schema_version":"1.0","source":{"id":"2309.03450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03450","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03450v1","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03450","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"pith_short_12","alias_value":"RWJM7VDI4FLC","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"pith_short_16","alias_value":"RWJM7VDI4FLCQLMD","created_at":"2026-07-05T06:48:28Z"},{"alias_kind":"pith_short_8","alias_value":"RWJM7VDI","created_at":"2026-07-05T06:48:28Z"}],"graph_snapshots":[{"event_id":"sha256:9d033b691893d5f87e96e83e43324791c9ea31dc9af4ba05429dc93a7237e531","target":"graph","created_at":"2026-07-05T06:48:28Z","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/2309.03450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary walls, hindering scientific progress. Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context. To address this, we have trained XGen, a series of 7B parameter models on up to 8K sequence length for up to 1.5T tokens. We have also finetuned the ","authors_text":"Alex Fabbri, Ben Krause, Bo Pang, Caiming Xiong, Chen Xing, Chien-Sheng Wu, Congying Xia, Erik Nijkamp, Hiroaki Hayashi, Jesse Vig, Lidiya Murakhovs'ka, Lifu Tu, Meghana Bhat, Philippe Laban, Prafulla Kumar Choubey, Rui Meng, Semih Yavuz, Senthil Purushwalkam, Shafiq Joty, Silvio Savarese, Tian Xie, Tong Niu, Wojciech Kry\\'sci\\'nski, Ye Liu, Yingbo Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-07T02:20:03Z","title":"XGen-7B Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03450","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":"sha256:596c8ad341592463b0a22e67a747b54ba9e248de5cfa7f53c9dfd7d75f188274","target":"record","created_at":"2026-07-05T06:48:28Z","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":"4e1a040fca84e871105dab14ec04dbb96ba914a94f297cf457de1b116e33c2af","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-07T02:20:03Z","title_canon_sha256":"cc01df77d3a1bbd1302852e5af08a75e767fafbf0e1abf2feda00d573bd08ceb"},"schema_version":"1.0","source":{"id":"2309.03450","kind":"arxiv","version":1}},"canonical_sha256":"8d92cfd468e156282d83021f29f0ae3c39987c6b59a9c06a82c5b3850a95d253","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d92cfd468e156282d83021f29f0ae3c39987c6b59a9c06a82c5b3850a95d253","first_computed_at":"2026-07-05T06:48:28.438865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:28.438865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nQ368Amb6F8n9gs6p1cH2Uns+Pn6xIbta2RJWEomVfaqwxmF4bs6YRg9uCJ3bKxPDnLmAvbKswMkFqy51+NeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:28.439345Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.03450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:596c8ad341592463b0a22e67a747b54ba9e248de5cfa7f53c9dfd7d75f188274","sha256:9d033b691893d5f87e96e83e43324791c9ea31dc9af4ba05429dc93a7237e531"],"state_sha256":"f64d7f364a82628a72336a7177d70a0b8f6d5e39ca5cb4c48c49fbedb9ca602c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izTlEgi6hJbaRvKizwURkZkJwg7Wfy7z25LIZmc7SWj7cYCqPCCCnkwE7X2Evl6dbNQExyMgM+2I+IhqliT1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:12:46.881998Z","bundle_sha256":"cd69951b95c3a5422b817d2745afd7abb8731e9fc2e4b19e796010eba0b12839"}}