{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BQ27STD2ZXZILZPHSUKGIS6H4O","short_pith_number":"pith:BQ27STD2","canonical_record":{"source":{"id":"2410.21252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T17:50:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"47249b42241155df93cc660f25a79793bfcdb99b09a9e962b5bbdd270ec03c98","abstract_canon_sha256":"241beb97e40c6ab495435093cd78cb090e1071a5390d05ef6ea172b8f6f95fd7"},"schema_version":"1.0"},"canonical_sha256":"0c35f94c7acdf285e5e79514644bc7e3a2a23d8c7292edb9349f43a57f3b6bb4","source":{"kind":"arxiv","id":"2410.21252","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21252","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21252v1","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21252","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_12","alias_value":"BQ27STD2ZXZI","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_16","alias_value":"BQ27STD2ZXZILZPH","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_8","alias_value":"BQ27STD2","created_at":"2026-07-05T09:27:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BQ27STD2ZXZILZPHSUKGIS6H4O","target":"record","payload":{"canonical_record":{"source":{"id":"2410.21252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T17:50:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"47249b42241155df93cc660f25a79793bfcdb99b09a9e962b5bbdd270ec03c98","abstract_canon_sha256":"241beb97e40c6ab495435093cd78cb090e1071a5390d05ef6ea172b8f6f95fd7"},"schema_version":"1.0"},"canonical_sha256":"0c35f94c7acdf285e5e79514644bc7e3a2a23d8c7292edb9349f43a57f3b6bb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:17.453067Z","signature_b64":"ku8gcIfKnglYV862I8ybKdxElfenort5H6Fvsx8wwCcr6mF1z7o4sVkt8O473h3JXeT4/dXd618K8DXMdEeaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c35f94c7acdf285e5e79514644bc7e3a2a23d8c7292edb9349f43a57f3b6bb4","last_reissued_at":"2026-07-05T09:27:17.452590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:17.452590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.21252","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":"2026-07-05T09:27:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5hmOfHivSOrnmgi1Y+mWbU2NjD3Azt7iIaQ8zhW54OIDqIvlCQI5OlVwmHZSIURyn1/+YqppRQTARy41oJtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:09:30.022383Z"},"content_sha256":"14cf94498d0c42e1752068d098da57f901865cec78214daea2253d704228676c","schema_version":"1.0","event_id":"sha256:14cf94498d0c42e1752068d098da57f901865cec78214daea2253d704228676c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BQ27STD2ZXZILZPHSUKGIS6H4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LongReward: Improving Long-context Large Language Models with AI Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiajie Zhang, Juanzi Li, Lei Hou, Ling Feng, Shulin Cao, Xin Lv, Yilin Niu, Yuxiao Dong, Zhenyu Hou, Zhongni Hou","submitted_at":"2024-10-28T17:50:42Z","abstract_excerpt":"Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT models and leads to inherent limitations. In principle, reinforcement learning (RL) with appropriate reward signals can further enhance models' capacities. However, how to obtain reliable rewards in long-context scenarios remains unexplored. To this end, we propose LongReward, a novel method that utilizes an off-the-shelf LLM to provide rewards for long-conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21252","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/2410.21252/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":"2026-07-05T09:27:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AZ6SmvQLOAM5SCgJzAe/8ZGim/MuCgt9VNq0VZParQ7bE3AUlSdrQw9M+SwljOUJi2CjZ3TtwxlSbBYGIenAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:09:30.022760Z"},"content_sha256":"3409db9ad089fbc4e79822db8731d5b43ae31b745c8411dc8e63c7a4f8958783","schema_version":"1.0","event_id":"sha256:3409db9ad089fbc4e79822db8731d5b43ae31b745c8411dc8e63c7a4f8958783"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQ27STD2ZXZILZPHSUKGIS6H4O/bundle.json","state_url":"https://pith.science/pith/BQ27STD2ZXZILZPHSUKGIS6H4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQ27STD2ZXZILZPHSUKGIS6H4O/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":"2026-07-06T08:09:30Z","links":{"resolver":"https://pith.science/pith/BQ27STD2ZXZILZPHSUKGIS6H4O","bundle":"https://pith.science/pith/BQ27STD2ZXZILZPHSUKGIS6H4O/bundle.json","state":"https://pith.science/pith/BQ27STD2ZXZILZPHSUKGIS6H4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQ27STD2ZXZILZPHSUKGIS6H4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQ27STD2ZXZILZPHSUKGIS6H4O","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":"241beb97e40c6ab495435093cd78cb090e1071a5390d05ef6ea172b8f6f95fd7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T17:50:42Z","title_canon_sha256":"47249b42241155df93cc660f25a79793bfcdb99b09a9e962b5bbdd270ec03c98"},"schema_version":"1.0","source":{"id":"2410.21252","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21252","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21252v1","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21252","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_12","alias_value":"BQ27STD2ZXZI","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_16","alias_value":"BQ27STD2ZXZILZPH","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_8","alias_value":"BQ27STD2","created_at":"2026-07-05T09:27:17Z"}],"graph_snapshots":[{"event_id":"sha256:3409db9ad089fbc4e79822db8731d5b43ae31b745c8411dc8e63c7a4f8958783","target":"graph","created_at":"2026-07-05T09:27:17Z","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/2410.21252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT models and leads to inherent limitations. In principle, reinforcement learning (RL) with appropriate reward signals can further enhance models' capacities. However, how to obtain reliable rewards in long-context scenarios remains unexplored. To this end, we propose LongReward, a novel method that utilizes an off-the-shelf LLM to provide rewards for long-conte","authors_text":"Jiajie Zhang, Juanzi Li, Lei Hou, Ling Feng, Shulin Cao, Xin Lv, Yilin Niu, Yuxiao Dong, Zhenyu Hou, Zhongni Hou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T17:50:42Z","title":"LongReward: Improving Long-context Large Language Models with AI Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21252","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":"sha256:14cf94498d0c42e1752068d098da57f901865cec78214daea2253d704228676c","target":"record","created_at":"2026-07-05T09:27:17Z","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":"241beb97e40c6ab495435093cd78cb090e1071a5390d05ef6ea172b8f6f95fd7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T17:50:42Z","title_canon_sha256":"47249b42241155df93cc660f25a79793bfcdb99b09a9e962b5bbdd270ec03c98"},"schema_version":"1.0","source":{"id":"2410.21252","kind":"arxiv","version":1}},"canonical_sha256":"0c35f94c7acdf285e5e79514644bc7e3a2a23d8c7292edb9349f43a57f3b6bb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c35f94c7acdf285e5e79514644bc7e3a2a23d8c7292edb9349f43a57f3b6bb4","first_computed_at":"2026-07-05T09:27:17.452590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:17.452590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ku8gcIfKnglYV862I8ybKdxElfenort5H6Fvsx8wwCcr6mF1z7o4sVkt8O473h3JXeT4/dXd618K8DXMdEeaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:17.453067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21252","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14cf94498d0c42e1752068d098da57f901865cec78214daea2253d704228676c","sha256:3409db9ad089fbc4e79822db8731d5b43ae31b745c8411dc8e63c7a4f8958783"],"state_sha256":"71cb19d62ab59a6dd8396a04a748440b76a82c6f3a311a6cda9fd376aac4ff9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4ExBFh2UyfQmv8n9sq3Bus0D+Uab173IQG21fEH8G3yKltqAvPDOFhYa28oLC85dNDZQo2iwbDvYwDrcAD0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:09:30.024718Z","bundle_sha256":"ed284ae277bc20409381422bbd79fdaefbec7e460df565a2b2a95a4c123731df"}}