{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L4ZLRM2TWCQTVBV7Z254OZWCBV","short_pith_number":"pith:L4ZLRM2T","canonical_record":{"source":{"id":"2503.23905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:54:55Z","cross_cats_sorted":[],"title_canon_sha256":"20359b3bc997bdcfa2f488c5f1e09dc4f9be28b0e21fb3fc29c672bce7aa434b","abstract_canon_sha256":"8cf2a92968c91ccd977aa5dbed1072fc4b9cecc94458cc9dcd27ccfd033f06b2"},"schema_version":"1.0"},"canonical_sha256":"5f32b8b353b0a13a86bfcebbc766c20d6343e70a0d240f68b4737d898947b7a1","source":{"kind":"arxiv","id":"2503.23905","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23905","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23905v2","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23905","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"L4ZLRM2TWCQT","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"L4ZLRM2TWCQTVBV7","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"L4ZLRM2T","created_at":"2026-07-05T11:28:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L4ZLRM2TWCQTVBV7Z254OZWCBV","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:54:55Z","cross_cats_sorted":[],"title_canon_sha256":"20359b3bc997bdcfa2f488c5f1e09dc4f9be28b0e21fb3fc29c672bce7aa434b","abstract_canon_sha256":"8cf2a92968c91ccd977aa5dbed1072fc4b9cecc94458cc9dcd27ccfd033f06b2"},"schema_version":"1.0"},"canonical_sha256":"5f32b8b353b0a13a86bfcebbc766c20d6343e70a0d240f68b4737d898947b7a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:15.461936Z","signature_b64":"XpatEuI/sY/MaV526m1jTiDUUPCeRBT93vDdEcq+iDmWIoqcamZLa1sJKfmokikXeSA0fstZ+VBv1SRSukHYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f32b8b353b0a13a86bfcebbc766c20d6343e70a0d240f68b4737d898947b7a1","last_reissued_at":"2026-07-05T11:28:15.461486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:15.461486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23905","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":"2026-07-05T11:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1oQ+QFv32x8PhlUwCihZ59bMXpUOY9ECpJ6gcoZJP+JQglFm/tFnuI54muEPO1i1BMCLV4eU027BbB63Ru8lCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:10:51.217894Z"},"content_sha256":"000d816d54a1885f9ed186e6dea6ee1dcf9defa6332234c3d7c1dd675f9324c7","schema_version":"1.0","event_id":"sha256:000d816d54a1885f9ed186e6dea6ee1dcf9defa6332234c3d7c1dd675f9324c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L4ZLRM2TWCQTVBV7Z254OZWCBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting MLLM Reasoning with Text-Debiased Hint-GRPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Yao, Hao Jiang, Jie Song, Jingyuan Chen, Jinlong Liu, Mingli Song, Qihan Huang, Wanggui He, Weilong Dai","submitted_at":"2025-03-31T09:54:55Z","abstract_excerpt":"MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate reasoning steps, and ORM, which supervises the final results. Recently, DeepSeek-R1 has challenged the traditional view that PRM outperforms ORM, which demonstrates strong generalization performance using an ORM method (i.e., GRPO). However, current MLLM's GRPO algorithms still struggle to handle challenging and complex multimodal reasoning tasks (e.g., mathematical reasoning). In this work, we reveal two problems that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23905","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/2503.23905/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":"2026-07-05T11:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4As/YoXB001MkANzQ6M2WlS5qV/ANMpX/3zMOrW/Bq+2vd80tTHtOzrkny1WFPW8rimw/vK9GVloYFTmsgfqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:10:51.218864Z"},"content_sha256":"5e8dea807346dccc4f15a3efe92c38c2448ab8f415beda136244d0de5baf960d","schema_version":"1.0","event_id":"sha256:5e8dea807346dccc4f15a3efe92c38c2448ab8f415beda136244d0de5baf960d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV/bundle.json","state_url":"https://pith.science/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV/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":"2026-08-03T18:10:51Z","links":{"resolver":"https://pith.science/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV","bundle":"https://pith.science/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV/bundle.json","state":"https://pith.science/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4ZLRM2TWCQTVBV7Z254OZWCBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L4ZLRM2TWCQTVBV7Z254OZWCBV","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":"8cf2a92968c91ccd977aa5dbed1072fc4b9cecc94458cc9dcd27ccfd033f06b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:54:55Z","title_canon_sha256":"20359b3bc997bdcfa2f488c5f1e09dc4f9be28b0e21fb3fc29c672bce7aa434b"},"schema_version":"1.0","source":{"id":"2503.23905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23905","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23905v2","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23905","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"L4ZLRM2TWCQT","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"L4ZLRM2TWCQTVBV7","created_at":"2026-07-05T11:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"L4ZLRM2T","created_at":"2026-07-05T11:28:15Z"}],"graph_snapshots":[{"event_id":"sha256:5e8dea807346dccc4f15a3efe92c38c2448ab8f415beda136244d0de5baf960d","target":"graph","created_at":"2026-07-05T11:28:15Z","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/2503.23905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate reasoning steps, and ORM, which supervises the final results. Recently, DeepSeek-R1 has challenged the traditional view that PRM outperforms ORM, which demonstrates strong generalization performance using an ORM method (i.e., GRPO). However, current MLLM's GRPO algorithms still struggle to handle challenging and complex multimodal reasoning tasks (e.g., mathematical reasoning). In this work, we reveal two problems that ","authors_text":"Chang Yao, Hao Jiang, Jie Song, Jingyuan Chen, Jinlong Liu, Mingli Song, Qihan Huang, Wanggui He, Weilong Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:54:55Z","title":"Boosting MLLM Reasoning with Text-Debiased Hint-GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23905","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":"sha256:000d816d54a1885f9ed186e6dea6ee1dcf9defa6332234c3d7c1dd675f9324c7","target":"record","created_at":"2026-07-05T11:28:15Z","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":"8cf2a92968c91ccd977aa5dbed1072fc4b9cecc94458cc9dcd27ccfd033f06b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:54:55Z","title_canon_sha256":"20359b3bc997bdcfa2f488c5f1e09dc4f9be28b0e21fb3fc29c672bce7aa434b"},"schema_version":"1.0","source":{"id":"2503.23905","kind":"arxiv","version":2}},"canonical_sha256":"5f32b8b353b0a13a86bfcebbc766c20d6343e70a0d240f68b4737d898947b7a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f32b8b353b0a13a86bfcebbc766c20d6343e70a0d240f68b4737d898947b7a1","first_computed_at":"2026-07-05T11:28:15.461486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:15.461486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XpatEuI/sY/MaV526m1jTiDUUPCeRBT93vDdEcq+iDmWIoqcamZLa1sJKfmokikXeSA0fstZ+VBv1SRSukHYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:15.461936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:000d816d54a1885f9ed186e6dea6ee1dcf9defa6332234c3d7c1dd675f9324c7","sha256:5e8dea807346dccc4f15a3efe92c38c2448ab8f415beda136244d0de5baf960d"],"state_sha256":"e9136cc568f8a79788b9cb19c52532f0ac2ce86dd1f17a6093319b897c80216c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxHnw9BYO0C5+9k7giBtXpTuSFcOZb8f37/s+Hetg0sO4P19I00NJdtvZVpLR4d9Qt02KWtMGt6i4SbndsAJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:10:51.226838Z","bundle_sha256":"2f70e951380f09ba604dd5f409aa66adbabdcfad800627a49775cf209c16be3d"}}