{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7D5I5VTSF24DF6SSMI4YEIPEHT","short_pith_number":"pith:7D5I5VTS","canonical_record":{"source":{"id":"2411.00809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T16:16:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c24abc72c5c663eac994255e0e08a72a766ca59793471841fc4cc390acb0aead","abstract_canon_sha256":"f1e1cc48f2d531c473e2006d0fbbb3bb0a3e1b093768b7b8b3aa6a3eece17f1a"},"schema_version":"1.0"},"canonical_sha256":"f8fa8ed6722eb832fa5262398221e43cd98094746a9cabcf0142c96891e51044","source":{"kind":"arxiv","id":"2411.00809","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00809","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00809v3","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00809","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"pith_short_12","alias_value":"7D5I5VTSF24D","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"pith_short_16","alias_value":"7D5I5VTSF24DF6SS","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"pith_short_8","alias_value":"7D5I5VTS","created_at":"2026-07-05T10:19:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7D5I5VTSF24DF6SSMI4YEIPEHT","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T16:16:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c24abc72c5c663eac994255e0e08a72a766ca59793471841fc4cc390acb0aead","abstract_canon_sha256":"f1e1cc48f2d531c473e2006d0fbbb3bb0a3e1b093768b7b8b3aa6a3eece17f1a"},"schema_version":"1.0"},"canonical_sha256":"f8fa8ed6722eb832fa5262398221e43cd98094746a9cabcf0142c96891e51044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:30.595795Z","signature_b64":"N2CBD8plyF1mqJcs6BjRIGGyxT+tWnuev1pPr/9ZrIlR/Ch1hAocJUUmTmFLsXaltPwGlhIK+6vW6anie6JmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8fa8ed6722eb832fa5262398221e43cd98094746a9cabcf0142c96891e51044","last_reissued_at":"2026-07-05T10:19:30.595353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:30.595353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00809","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":"2026-07-05T10:19:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUIW2/rfXmPPJ/2Yl0rQr8CFqi1agsHY0oWCN1EAjwrYFf29dVGkihcFbQK6CLgnDkdlVv6X09KmMmMy+4muBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T03:06:36.028952Z"},"content_sha256":"ebd4b74adbc01ec8d53fc1a1d14dbd90a36082f5b9a1a97e52e9a7095aee835f","schema_version":"1.0","event_id":"sha256:ebd4b74adbc01ec8d53fc1a1d14dbd90a36082f5b9a1a97e52e9a7095aee835f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7D5I5VTSF24DF6SSMI4YEIPEHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Zheng, Gengru Chen, Shaopan Xiong, Wenbo Su, Xiaoyang Li, Xingyuan Bu, Yanshi Li, Yijia Luo, Yingshui Tan","submitted_at":"2024-10-23T16:16:15Z","abstract_excerpt":"Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This reflects a key credit assignment problem: identifying which tokens to reinforce or suppress. To rectify these shortcomings, step-wise and token-wise methods have been proposed. However, step-wise methods rely on punctuation segmentation and still cannot accurately identify the key tokens. The token-level approach is too fine-grained, attending to many unimporta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00809","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/2411.00809/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":"2026-07-05T10:19:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zfboh/yexKVHDPVlVj0qiT7sIc6yOuV8r1Eh58Qbp+S8EZEiHbkgSmIyjw6SSYH1dQacKL6YMAr3lHeJtFsLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T03:06:36.029381Z"},"content_sha256":"87538d70ec41c6ea64d87b83e4b7844c0e3b6c6f130222c8a1352d832841a5ec","schema_version":"1.0","event_id":"sha256:87538d70ec41c6ea64d87b83e4b7844c0e3b6c6f130222c8a1352d832841a5ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7D5I5VTSF24DF6SSMI4YEIPEHT/bundle.json","state_url":"https://pith.science/pith/7D5I5VTSF24DF6SSMI4YEIPEHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7D5I5VTSF24DF6SSMI4YEIPEHT/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":"2026-07-10T03:06:36Z","links":{"resolver":"https://pith.science/pith/7D5I5VTSF24DF6SSMI4YEIPEHT","bundle":"https://pith.science/pith/7D5I5VTSF24DF6SSMI4YEIPEHT/bundle.json","state":"https://pith.science/pith/7D5I5VTSF24DF6SSMI4YEIPEHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7D5I5VTSF24DF6SSMI4YEIPEHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7D5I5VTSF24DF6SSMI4YEIPEHT","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":"f1e1cc48f2d531c473e2006d0fbbb3bb0a3e1b093768b7b8b3aa6a3eece17f1a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T16:16:15Z","title_canon_sha256":"c24abc72c5c663eac994255e0e08a72a766ca59793471841fc4cc390acb0aead"},"schema_version":"1.0","source":{"id":"2411.00809","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00809","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00809v3","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00809","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"pith_short_12","alias_value":"7D5I5VTSF24D","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"pith_short_16","alias_value":"7D5I5VTSF24DF6SS","created_at":"2026-07-05T10:19:30Z"},{"alias_kind":"pith_short_8","alias_value":"7D5I5VTS","created_at":"2026-07-05T10:19:30Z"}],"graph_snapshots":[{"event_id":"sha256:87538d70ec41c6ea64d87b83e4b7844c0e3b6c6f130222c8a1352d832841a5ec","target":"graph","created_at":"2026-07-05T10:19:30Z","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/2411.00809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This reflects a key credit assignment problem: identifying which tokens to reinforce or suppress. To rectify these shortcomings, step-wise and token-wise methods have been proposed. However, step-wise methods rely on punctuation segmentation and still cannot accurately identify the key tokens. The token-level approach is too fine-grained, attending to many unimporta","authors_text":"Bo Zheng, Gengru Chen, Shaopan Xiong, Wenbo Su, Xiaoyang Li, Xingyuan Bu, Yanshi Li, Yijia Luo, Yingshui Tan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T16:16:15Z","title":"Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00809","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:ebd4b74adbc01ec8d53fc1a1d14dbd90a36082f5b9a1a97e52e9a7095aee835f","target":"record","created_at":"2026-07-05T10:19:30Z","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":"f1e1cc48f2d531c473e2006d0fbbb3bb0a3e1b093768b7b8b3aa6a3eece17f1a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T16:16:15Z","title_canon_sha256":"c24abc72c5c663eac994255e0e08a72a766ca59793471841fc4cc390acb0aead"},"schema_version":"1.0","source":{"id":"2411.00809","kind":"arxiv","version":3}},"canonical_sha256":"f8fa8ed6722eb832fa5262398221e43cd98094746a9cabcf0142c96891e51044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8fa8ed6722eb832fa5262398221e43cd98094746a9cabcf0142c96891e51044","first_computed_at":"2026-07-05T10:19:30.595353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:30.595353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N2CBD8plyF1mqJcs6BjRIGGyxT+tWnuev1pPr/9ZrIlR/Ch1hAocJUUmTmFLsXaltPwGlhIK+6vW6anie6JmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:30.595795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00809","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebd4b74adbc01ec8d53fc1a1d14dbd90a36082f5b9a1a97e52e9a7095aee835f","sha256:87538d70ec41c6ea64d87b83e4b7844c0e3b6c6f130222c8a1352d832841a5ec"],"state_sha256":"48b4fc9f6cb11039de96eb4667dff9a3fe9ec7155c284e091d65598f82c1b8b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtSXpcUPmuLZD/zVf5PuiQKUo2yjoMQNAAX0m2YyQEt3yckv+ZRHlwVlvyCLANQX4/LdhHC+dYaCOEhzts0TBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T03:06:36.031418Z","bundle_sha256":"d6c9088920411abd70df62a71fe9da9dfc0933968ce8a1f76f0defa09d42a0f7"}}