{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IKNGNW32J2WS73OWKQSMJB6DHF","short_pith_number":"pith:IKNGNW32","canonical_record":{"source":{"id":"2506.03038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"d947de77251b5cdd2bc394be3117e8df1ccb9a43e5d1af0e16ffae9c0ce2ce96","abstract_canon_sha256":"ede53d742f0c5b480348d76f6989c0d4d3423224f9b00581168095ab8f23aa81"},"schema_version":"1.0"},"canonical_sha256":"429a66db7a4ead2fedd65424c487c33942202b6d43926803d5e92d793307d83a","source":{"kind":"arxiv","id":"2506.03038","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03038","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03038v2","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03038","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"IKNGNW32J2WS","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"IKNGNW32J2WS73OW","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"IKNGNW32","created_at":"2026-07-05T11:17:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IKNGNW32J2WS73OWKQSMJB6DHF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"d947de77251b5cdd2bc394be3117e8df1ccb9a43e5d1af0e16ffae9c0ce2ce96","abstract_canon_sha256":"ede53d742f0c5b480348d76f6989c0d4d3423224f9b00581168095ab8f23aa81"},"schema_version":"1.0"},"canonical_sha256":"429a66db7a4ead2fedd65424c487c33942202b6d43926803d5e92d793307d83a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:46.957008Z","signature_b64":"54P+C/ecbBFZj3Z8nBgmcwzI6N14c8ZffaNby82LEtPvv686qW1+maKOSBpvv+1hFZfmXfN1RrYg3Nmez4wpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"429a66db7a4ead2fedd65424c487c33942202b6d43926803d5e92d793307d83a","last_reissued_at":"2026-07-05T11:17:46.956595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:46.956595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03038","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lsLPZxIEnksPKi2pDqzVsFPG8Db7aGl6X5cpogpc2m/T2MOIwVCs/jYRXLPt/7mdiipUGByVICa2J3IErmMzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:52:14.373220Z"},"content_sha256":"9daf9e95d306cdd6a9ff98bc3bc883b3928de08e390d98627097cc079db70263","schema_version":"1.0","event_id":"sha256:9daf9e95d306cdd6a9ff98bc3bc883b3928de08e390d98627097cc079db70263"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IKNGNW32J2WS73OWKQSMJB6DHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jintian Shao, Yiming Cheng","submitted_at":"2025-06-03T16:20:47Z","abstract_excerpt":"Reinforcement learning (RL) enhances large language models (LLMs) in complex, long-chain-of-thought (long-CoT) reasoning. The advanced VAPO framework, despite sophisticated mechanisms like Decoupled GAE, theoretically faces fundamental limitations in comprehensively modeling and leveraging deep, long-term value for fine-grained, step-by-step policy guidance in extended reasoning chains. We argue these limitations stem from inherent difficulties in credit assignment, value function representational capacity with temporally abstracted goals, and translating global value signals into local policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03038","kind":"arxiv","version":2},"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/2506.03038/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":"2026-07-05T11:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QgKH8abfF8D9LbIYF02pgpPox4wvzr3h8SpU/bWJL+aVJEilYeTs8/zcEp+24T4HoQv6/Wqo7gA0jOeZCdfCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:52:14.374170Z"},"content_sha256":"501e01e64056c7696af8868ddec36989e0e24ccc03f9b8713a074d71dbe06b62","schema_version":"1.0","event_id":"sha256:501e01e64056c7696af8868ddec36989e0e24ccc03f9b8713a074d71dbe06b62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKNGNW32J2WS73OWKQSMJB6DHF/bundle.json","state_url":"https://pith.science/pith/IKNGNW32J2WS73OWKQSMJB6DHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKNGNW32J2WS73OWKQSMJB6DHF/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":"2026-08-07T16:52:14Z","links":{"resolver":"https://pith.science/pith/IKNGNW32J2WS73OWKQSMJB6DHF","bundle":"https://pith.science/pith/IKNGNW32J2WS73OWKQSMJB6DHF/bundle.json","state":"https://pith.science/pith/IKNGNW32J2WS73OWKQSMJB6DHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKNGNW32J2WS73OWKQSMJB6DHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IKNGNW32J2WS73OWKQSMJB6DHF","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":"ede53d742f0c5b480348d76f6989c0d4d3423224f9b00581168095ab8f23aa81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:20:47Z","title_canon_sha256":"d947de77251b5cdd2bc394be3117e8df1ccb9a43e5d1af0e16ffae9c0ce2ce96"},"schema_version":"1.0","source":{"id":"2506.03038","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03038","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03038v2","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03038","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"IKNGNW32J2WS","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"IKNGNW32J2WS73OW","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"IKNGNW32","created_at":"2026-07-05T11:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:501e01e64056c7696af8868ddec36989e0e24ccc03f9b8713a074d71dbe06b62","target":"graph","created_at":"2026-07-05T11:17:46Z","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/2506.03038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) enhances large language models (LLMs) in complex, long-chain-of-thought (long-CoT) reasoning. The advanced VAPO framework, despite sophisticated mechanisms like Decoupled GAE, theoretically faces fundamental limitations in comprehensively modeling and leveraging deep, long-term value for fine-grained, step-by-step policy guidance in extended reasoning chains. We argue these limitations stem from inherent difficulties in credit assignment, value function representational capacity with temporally abstracted goals, and translating global value signals into local policy","authors_text":"Jintian Shao, Yiming Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:20:47Z","title":"Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03038","kind":"arxiv","version":2},"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":"sha256:9daf9e95d306cdd6a9ff98bc3bc883b3928de08e390d98627097cc079db70263","target":"record","created_at":"2026-07-05T11:17:46Z","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":"ede53d742f0c5b480348d76f6989c0d4d3423224f9b00581168095ab8f23aa81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:20:47Z","title_canon_sha256":"d947de77251b5cdd2bc394be3117e8df1ccb9a43e5d1af0e16ffae9c0ce2ce96"},"schema_version":"1.0","source":{"id":"2506.03038","kind":"arxiv","version":2}},"canonical_sha256":"429a66db7a4ead2fedd65424c487c33942202b6d43926803d5e92d793307d83a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"429a66db7a4ead2fedd65424c487c33942202b6d43926803d5e92d793307d83a","first_computed_at":"2026-07-05T11:17:46.956595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:46.956595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54P+C/ecbBFZj3Z8nBgmcwzI6N14c8ZffaNby82LEtPvv686qW1+maKOSBpvv+1hFZfmXfN1RrYg3Nmez4wpDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:46.957008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03038","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9daf9e95d306cdd6a9ff98bc3bc883b3928de08e390d98627097cc079db70263","sha256:501e01e64056c7696af8868ddec36989e0e24ccc03f9b8713a074d71dbe06b62"],"state_sha256":"845393fa6bea47aa00fd7305058c8308c68b6920c7ee759191a213efc6e194a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ojR+6Bl6ouYCWQOFVmNddDRsVDmBjbWXggOy9Vr4/SOe3p7PTQNo2gi8Sh26q8KT+aIFd27KWVv85Hxh9y+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:52:14.381355Z","bundle_sha256":"d23bd17023dc53dc90bea24fd677915d5a8e5243463994d535a77862cd92a926"}}