{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SRURYCFQOORMU5VGM4S6RBKHQT","short_pith_number":"pith:SRURYCFQ","canonical_record":{"source":{"id":"2512.10414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-12-11T08:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"01b4e05bd8015763492d2e4c02cecddc53dde9a66c51fddebd14090fdcf2a72a","abstract_canon_sha256":"bb28fdd8e23312f266230d67c577ad6ebb8e87864794e410221d49e07ade427e"},"schema_version":"1.0"},"canonical_sha256":"94691c08b073a2ca76a66725e8854784c40fde6199686a002ce85965a7480b33","source":{"kind":"arxiv","id":"2512.10414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10414","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10414v2","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10414","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"SRURYCFQOORM","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"SRURYCFQOORMU5VG","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"SRURYCFQ","created_at":"2026-06-02T01:03:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SRURYCFQOORMU5VGM4S6RBKHQT","target":"record","payload":{"canonical_record":{"source":{"id":"2512.10414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-12-11T08:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"01b4e05bd8015763492d2e4c02cecddc53dde9a66c51fddebd14090fdcf2a72a","abstract_canon_sha256":"bb28fdd8e23312f266230d67c577ad6ebb8e87864794e410221d49e07ade427e"},"schema_version":"1.0"},"canonical_sha256":"94691c08b073a2ca76a66725e8854784c40fde6199686a002ce85965a7480b33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:39.709302Z","signature_b64":"KrRM8SnSVmN88Cwz47gYEk6e703Mck4ljW9kH0RSVEoG+hVIxnIyc/cgajefkaSZmsu10EKvqsw4vQEYwAOHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94691c08b073a2ca76a66725e8854784c40fde6199686a002ce85965a7480b33","last_reissued_at":"2026-06-02T01:03:39.708760Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:39.708760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.10414","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":"2026-06-02T01:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1d4BOOpNBBV8Ob67uyNk7zEEdTgGxNp8dP2N7N8XDi5SiqzESSQJbRxslGFm69+PEjts//dKlt/UA4h049RDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T10:27:42.951241Z"},"content_sha256":"fcb9858111ff5492d1b72c3031312f50857a52e01f66b3d9a93e9f6b7ddebab6","schema_version":"1.0","event_id":"sha256:fcb9858111ff5492d1b72c3031312f50857a52e01f66b3d9a93e9f6b7ddebab6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SRURYCFQOORMU5VGM4S6RBKHQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lanqing Li, Xiaomeng Li, Yang Yu, ZhuangZhuang Chen","submitted_at":"2025-12-11T08:27:02Z","abstract_excerpt":"Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective way to benefit exploratory ability, thereby improving policy performance. Notably, most existing studies intervene in entropy by simply controlling the update of specific tokens during policy optimization of RL. They ignore the entropy intervention during the RL sampling that can boost the performance of GRPO by improving the diversity of responses. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10414","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/2512.10414/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":"2026-06-02T01:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0KuMqhKBtqDeIJ5qszA9uObQnjeVbZnTXqP+wWj6f+8I1jkxNc2ikWzMg9WmsPbHa/EaCrlrU9d2yz2ZtxlZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T10:27:42.951618Z"},"content_sha256":"b1db2336e3de90899b8e1470d13ceafe0f0abbfebfd00a2ebc40cfa3134d9428","schema_version":"1.0","event_id":"sha256:b1db2336e3de90899b8e1470d13ceafe0f0abbfebfd00a2ebc40cfa3134d9428"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRURYCFQOORMU5VGM4S6RBKHQT/bundle.json","state_url":"https://pith.science/pith/SRURYCFQOORMU5VGM4S6RBKHQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRURYCFQOORMU5VGM4S6RBKHQT/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":"2026-06-20T10:27:42Z","links":{"resolver":"https://pith.science/pith/SRURYCFQOORMU5VGM4S6RBKHQT","bundle":"https://pith.science/pith/SRURYCFQOORMU5VGM4S6RBKHQT/bundle.json","state":"https://pith.science/pith/SRURYCFQOORMU5VGM4S6RBKHQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRURYCFQOORMU5VGM4S6RBKHQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SRURYCFQOORMU5VGM4S6RBKHQT","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":"bb28fdd8e23312f266230d67c577ad6ebb8e87864794e410221d49e07ade427e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-12-11T08:27:02Z","title_canon_sha256":"01b4e05bd8015763492d2e4c02cecddc53dde9a66c51fddebd14090fdcf2a72a"},"schema_version":"1.0","source":{"id":"2512.10414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10414","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10414v2","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10414","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"SRURYCFQOORM","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"SRURYCFQOORMU5VG","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"SRURYCFQ","created_at":"2026-06-02T01:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:b1db2336e3de90899b8e1470d13ceafe0f0abbfebfd00a2ebc40cfa3134d9428","target":"graph","created_at":"2026-06-02T01:03:39Z","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/2512.10414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective way to benefit exploratory ability, thereby improving policy performance. Notably, most existing studies intervene in entropy by simply controlling the update of specific tokens during policy optimization of RL. They ignore the entropy intervention during the RL sampling that can boost the performance of GRPO by improving the diversity of responses. In this p","authors_text":"Lanqing Li, Xiaomeng Li, Yang Yu, ZhuangZhuang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-12-11T08:27:02Z","title":"Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10414","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:fcb9858111ff5492d1b72c3031312f50857a52e01f66b3d9a93e9f6b7ddebab6","target":"record","created_at":"2026-06-02T01:03:39Z","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":"bb28fdd8e23312f266230d67c577ad6ebb8e87864794e410221d49e07ade427e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-12-11T08:27:02Z","title_canon_sha256":"01b4e05bd8015763492d2e4c02cecddc53dde9a66c51fddebd14090fdcf2a72a"},"schema_version":"1.0","source":{"id":"2512.10414","kind":"arxiv","version":2}},"canonical_sha256":"94691c08b073a2ca76a66725e8854784c40fde6199686a002ce85965a7480b33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94691c08b073a2ca76a66725e8854784c40fde6199686a002ce85965a7480b33","first_computed_at":"2026-06-02T01:03:39.708760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:39.708760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KrRM8SnSVmN88Cwz47gYEk6e703Mck4ljW9kH0RSVEoG+hVIxnIyc/cgajefkaSZmsu10EKvqsw4vQEYwAOHBw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:39.709302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.10414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcb9858111ff5492d1b72c3031312f50857a52e01f66b3d9a93e9f6b7ddebab6","sha256:b1db2336e3de90899b8e1470d13ceafe0f0abbfebfd00a2ebc40cfa3134d9428"],"state_sha256":"cf3df196073c67d054fbbdf2f497a24740b6adcd876d4c4e401c9e20e2234beb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhGa2cejnj3ab4pAztMVioc6jzh0jkolxXprQPoPgyn0iGxvx13rFxMNXq5J7krglVOkh4EjFnQoqehsfwI8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T10:27:42.953507Z","bundle_sha256":"ef866bfa3005b5961c468f5bf835853ada97a1e1e82cdf15eb9d037cec7de445"}}