{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UB2L5KJTYSIVJ4YG324HFI4V6R","short_pith_number":"pith:UB2L5KJT","canonical_record":{"source":{"id":"2501.06186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T18:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"c533093a0ba5949ec5f8a21c8d33d9211036024b4b8e2ab53d51bfe19882b465","abstract_canon_sha256":"5f21656e70ca6ae8c59d6bd4cf420ff3974002a70beb6e0393cca73b7f0b1dc7"},"schema_version":"1.0"},"canonical_sha256":"a074bea933c49154f306deb872a395f46bdc6732f1534821b267b113f7c3affa","source":{"kind":"arxiv","id":"2501.06186","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06186","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06186v1","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06186","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"UB2L5KJTYSIV","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"UB2L5KJTYSIVJ4YG","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"UB2L5KJT","created_at":"2026-07-05T09:59:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UB2L5KJTYSIVJ4YG324HFI4V6R","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T18:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"c533093a0ba5949ec5f8a21c8d33d9211036024b4b8e2ab53d51bfe19882b465","abstract_canon_sha256":"5f21656e70ca6ae8c59d6bd4cf420ff3974002a70beb6e0393cca73b7f0b1dc7"},"schema_version":"1.0"},"canonical_sha256":"a074bea933c49154f306deb872a395f46bdc6732f1534821b267b113f7c3affa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:34.405652Z","signature_b64":"JHy91/vbBM9Qx+unOYgxYHFxT0s1uDs6rW3LG2Yu3Oq94vD2ErV0cvMWJtt9+Rgymr8VViatkVV8qA0u1LzYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a074bea933c49154f306deb872a395f46bdc6732f1534821b267b113f7c3affa","last_reissued_at":"2026-07-05T09:59:34.405094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:34.405094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06186","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ku7rSricXRkrhHPIgPOf/auiElLLScrA7hvrFsc+esXo+WrNt8sQzhn39bStTdRGwRgKyV3aQU9ncYSNmNEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:31.207631Z"},"content_sha256":"6c1e8e66b0a52dad5ae848de6e66d36f4616ca737cc02f85ff37d59ae2f01307","schema_version":"1.0","event_id":"sha256:6c1e8e66b0a52dad5ae848de6e66d36f4616ca737cc02f85ff37d59ae2f01307"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UB2L5KJTYSIVJ4YG324HFI4V6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Heakl, Dinura Dissanayake, Fahad Shahbaz Khan, Hisham Cholakkal, Ivan Laptev, Jean Lahoud, Ketan More, Mohammed Zumri, Mubarak Shah, Noor Ahsan, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Yuhao Li","submitted_at":"2025-01-10T18:59:51Z","abstract_excerpt":"Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06186","kind":"arxiv","version":1},"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/2501.06186/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":"2026-07-05T09:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JPzydr33qkla/5Xxigu2oP+8SnmbG/hY2NMEgv+LzGbCUQLAiIXGUTv0nMVHvoy4LxnrwLMVApR8Ja55A1eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:59:31.207998Z"},"content_sha256":"4ec8007e0c9578e887ceab41fb2adbdedb6dba0360c5e27f72e3895e7899712e","schema_version":"1.0","event_id":"sha256:4ec8007e0c9578e887ceab41fb2adbdedb6dba0360c5e27f72e3895e7899712e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UB2L5KJTYSIVJ4YG324HFI4V6R/bundle.json","state_url":"https://pith.science/pith/UB2L5KJTYSIVJ4YG324HFI4V6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UB2L5KJTYSIVJ4YG324HFI4V6R/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":"2026-07-06T20:59:31Z","links":{"resolver":"https://pith.science/pith/UB2L5KJTYSIVJ4YG324HFI4V6R","bundle":"https://pith.science/pith/UB2L5KJTYSIVJ4YG324HFI4V6R/bundle.json","state":"https://pith.science/pith/UB2L5KJTYSIVJ4YG324HFI4V6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UB2L5KJTYSIVJ4YG324HFI4V6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UB2L5KJTYSIVJ4YG324HFI4V6R","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":"5f21656e70ca6ae8c59d6bd4cf420ff3974002a70beb6e0393cca73b7f0b1dc7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T18:59:51Z","title_canon_sha256":"c533093a0ba5949ec5f8a21c8d33d9211036024b4b8e2ab53d51bfe19882b465"},"schema_version":"1.0","source":{"id":"2501.06186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06186","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06186v1","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06186","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"UB2L5KJTYSIV","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"UB2L5KJTYSIVJ4YG","created_at":"2026-07-05T09:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"UB2L5KJT","created_at":"2026-07-05T09:59:34Z"}],"graph_snapshots":[{"event_id":"sha256:4ec8007e0c9578e887ceab41fb2adbdedb6dba0360c5e27f72e3895e7899712e","target":"graph","created_at":"2026-07-05T09:59:34Z","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/2501.06186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse ","authors_text":"Ahmed Heakl, Dinura Dissanayake, Fahad Shahbaz Khan, Hisham Cholakkal, Ivan Laptev, Jean Lahoud, Ketan More, Mohammed Zumri, Mubarak Shah, Noor Ahsan, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Yuhao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T18:59:51Z","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06186","kind":"arxiv","version":1},"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":"sha256:6c1e8e66b0a52dad5ae848de6e66d36f4616ca737cc02f85ff37d59ae2f01307","target":"record","created_at":"2026-07-05T09:59:34Z","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":"5f21656e70ca6ae8c59d6bd4cf420ff3974002a70beb6e0393cca73b7f0b1dc7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T18:59:51Z","title_canon_sha256":"c533093a0ba5949ec5f8a21c8d33d9211036024b4b8e2ab53d51bfe19882b465"},"schema_version":"1.0","source":{"id":"2501.06186","kind":"arxiv","version":1}},"canonical_sha256":"a074bea933c49154f306deb872a395f46bdc6732f1534821b267b113f7c3affa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a074bea933c49154f306deb872a395f46bdc6732f1534821b267b113f7c3affa","first_computed_at":"2026-07-05T09:59:34.405094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:34.405094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHy91/vbBM9Qx+unOYgxYHFxT0s1uDs6rW3LG2Yu3Oq94vD2ErV0cvMWJtt9+Rgymr8VViatkVV8qA0u1LzYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:34.405652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c1e8e66b0a52dad5ae848de6e66d36f4616ca737cc02f85ff37d59ae2f01307","sha256:4ec8007e0c9578e887ceab41fb2adbdedb6dba0360c5e27f72e3895e7899712e"],"state_sha256":"f36889a2061c4611e32ec7a99728dc761e97b00fd77e43468f3049960bdad0f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dR1JlTHfmL0nwBsS5l5PbhF+9hWj9WFH498A26Q623CpA5eQ4xec1yS/gtCpscUdS+5vaVwfB3Jm5VUNK1DsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:59:31.209967Z","bundle_sha256":"bdb488541943836acbafb5394b8d0123ed9960acbe54203f32960d9571accd45"}}