{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C5EOAUZNKECRTFRIVWAS5MMNX2","short_pith_number":"pith:C5EOAUZN","canonical_record":{"source":{"id":"2504.02587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T13:53:28Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"6909378d23a4ce5f379dccba2f0d61c6db2489dec07ebade0c8aec32557ab3a5","abstract_canon_sha256":"60f9fd4875bea75fe4789775d6e5eac9c4db2666bb7feba501032086295e2091"},"schema_version":"1.0"},"canonical_sha256":"1748e0532d5105199628ad812eb18dbea39002beb6083d42f2cd15c1a09fe8e2","source":{"kind":"arxiv","id":"2504.02587","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02587","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02587v2","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02587","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"C5EOAUZNKECR","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"C5EOAUZNKECRTFRI","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"C5EOAUZN","created_at":"2026-07-05T10:44:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C5EOAUZNKECRTFRIVWAS5MMNX2","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T13:53:28Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"6909378d23a4ce5f379dccba2f0d61c6db2489dec07ebade0c8aec32557ab3a5","abstract_canon_sha256":"60f9fd4875bea75fe4789775d6e5eac9c4db2666bb7feba501032086295e2091"},"schema_version":"1.0"},"canonical_sha256":"1748e0532d5105199628ad812eb18dbea39002beb6083d42f2cd15c1a09fe8e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:23.986845Z","signature_b64":"uQ3NprjV0YFcebaN7g/Ls5BRelrAI6SRawgmfKbyYhu4cypK2AhTMvQlSYaVInWNhG18sbO0kNEAzI7MoARtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1748e0532d5105199628ad812eb18dbea39002beb6083d42f2cd15c1a09fe8e2","last_reissued_at":"2026-07-05T10:44:23.986365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:23.986365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02587","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":"2026-07-05T10:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9o6rW4S6tWxUfo4tnONAkEgy/g5aDVTsKX9p4edJqLaJZRNec1OPLooPGsimc/6Siz9gWLsICReXEKXlQvSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:33:17.090231Z"},"content_sha256":"b18f0a77f80312d7134ae87749eedba9546eec8caa480305dc334a7f8d9123be","schema_version":"1.0","event_id":"sha256:b18f0a77f80312d7134ae87749eedba9546eec8caa480305dc334a7f8d9123be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C5EOAUZNKECRTFRIVWAS5MMNX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Pengfei Liu, Steffi Chern, Xuyang Shen, Yan Ma, Yiran Zhong","submitted_at":"2025-04-03T13:53:28Z","abstract_excerpt":"Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs often rely on heavily engineered frameworks that hinder reproducibility and accessibility, while lacking standardized evaluation protocols, making it difficult to compare results or interpret training dynamics. This work introduces a transparent, from-scratch framework for RL in VLMs, offering a minimal yet functional four-step pipeline validated across mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02587","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/2504.02587/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":"2026-07-05T10:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIljHqFOAl/UNbI4pj9W7O3yLsjuvy3DRa5FwOH45N9BY57ND0ZRYx3enr/ViGjzp95P7H2Ys0qDh6l3JxgLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:33:17.090735Z"},"content_sha256":"6aeba02398a879fa4866b958ce9ad939106112276fcab21e51e09f18b54fd3ba","schema_version":"1.0","event_id":"sha256:6aeba02398a879fa4866b958ce9ad939106112276fcab21e51e09f18b54fd3ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5EOAUZNKECRTFRIVWAS5MMNX2/bundle.json","state_url":"https://pith.science/pith/C5EOAUZNKECRTFRIVWAS5MMNX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5EOAUZNKECRTFRIVWAS5MMNX2/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":"2026-08-16T01:33:17Z","links":{"resolver":"https://pith.science/pith/C5EOAUZNKECRTFRIVWAS5MMNX2","bundle":"https://pith.science/pith/C5EOAUZNKECRTFRIVWAS5MMNX2/bundle.json","state":"https://pith.science/pith/C5EOAUZNKECRTFRIVWAS5MMNX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5EOAUZNKECRTFRIVWAS5MMNX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C5EOAUZNKECRTFRIVWAS5MMNX2","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":"60f9fd4875bea75fe4789775d6e5eac9c4db2666bb7feba501032086295e2091","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T13:53:28Z","title_canon_sha256":"6909378d23a4ce5f379dccba2f0d61c6db2489dec07ebade0c8aec32557ab3a5"},"schema_version":"1.0","source":{"id":"2504.02587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02587","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02587v2","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02587","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"C5EOAUZNKECR","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_16","alias_value":"C5EOAUZNKECRTFRI","created_at":"2026-07-05T10:44:23Z"},{"alias_kind":"pith_short_8","alias_value":"C5EOAUZN","created_at":"2026-07-05T10:44:23Z"}],"graph_snapshots":[{"event_id":"sha256:6aeba02398a879fa4866b958ce9ad939106112276fcab21e51e09f18b54fd3ba","target":"graph","created_at":"2026-07-05T10:44:23Z","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/2504.02587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs often rely on heavily engineered frameworks that hinder reproducibility and accessibility, while lacking standardized evaluation protocols, making it difficult to compare results or interpret training dynamics. This work introduces a transparent, from-scratch framework for RL in VLMs, offering a minimal yet functional four-step pipeline validated across mult","authors_text":"Pengfei Liu, Steffi Chern, Xuyang Shen, Yan Ma, Yiran Zhong","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T13:53:28Z","title":"Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02587","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:b18f0a77f80312d7134ae87749eedba9546eec8caa480305dc334a7f8d9123be","target":"record","created_at":"2026-07-05T10:44:23Z","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":"60f9fd4875bea75fe4789775d6e5eac9c4db2666bb7feba501032086295e2091","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T13:53:28Z","title_canon_sha256":"6909378d23a4ce5f379dccba2f0d61c6db2489dec07ebade0c8aec32557ab3a5"},"schema_version":"1.0","source":{"id":"2504.02587","kind":"arxiv","version":2}},"canonical_sha256":"1748e0532d5105199628ad812eb18dbea39002beb6083d42f2cd15c1a09fe8e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1748e0532d5105199628ad812eb18dbea39002beb6083d42f2cd15c1a09fe8e2","first_computed_at":"2026-07-05T10:44:23.986365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:23.986365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQ3NprjV0YFcebaN7g/Ls5BRelrAI6SRawgmfKbyYhu4cypK2AhTMvQlSYaVInWNhG18sbO0kNEAzI7MoARtCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:23.986845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b18f0a77f80312d7134ae87749eedba9546eec8caa480305dc334a7f8d9123be","sha256:6aeba02398a879fa4866b958ce9ad939106112276fcab21e51e09f18b54fd3ba"],"state_sha256":"fbce6d8426528598e567fe750fa516b29235d34a20690e715486df73a4d6b4a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GOGoD90uaH2IzgaC3tAJrlNpWM53+PdDT0Tba9W8FR26OZI2x8j4KI2QM7ZFbGLhmQd0xRj9QcKrkre4xit6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:33:17.094402Z","bundle_sha256":"df094218922ea0e54f4fbcfe1f95aa39730cbbfb01e215889bfda5aee36bc5cf"}}