{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N2HDJET6FV374VSK76UE7VCI5D","short_pith_number":"pith:N2HDJET6","canonical_record":{"source":{"id":"2501.02964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T12:16:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"60238a67caa664d27c3a43e3db3f4dba52a8e858f1090907ddc67f1f9e209f4d","abstract_canon_sha256":"89e4ba227902b2ac35e26d030f60865c77b40a262671dd56f84a4a34fc3d81a4"},"schema_version":"1.0"},"canonical_sha256":"6e8e34927e2d77fe564affa84fd448e8fb11b2debdb3120f5db54cd92d8533f8","source":{"kind":"arxiv","id":"2501.02964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02964","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02964v2","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02964","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_12","alias_value":"N2HDJET6FV37","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_16","alias_value":"N2HDJET6FV374VSK","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_8","alias_value":"N2HDJET6","created_at":"2026-07-05T09:57:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N2HDJET6FV374VSK76UE7VCI5D","target":"record","payload":{"canonical_record":{"source":{"id":"2501.02964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T12:16:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"60238a67caa664d27c3a43e3db3f4dba52a8e858f1090907ddc67f1f9e209f4d","abstract_canon_sha256":"89e4ba227902b2ac35e26d030f60865c77b40a262671dd56f84a4a34fc3d81a4"},"schema_version":"1.0"},"canonical_sha256":"6e8e34927e2d77fe564affa84fd448e8fb11b2debdb3120f5db54cd92d8533f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:50.897473Z","signature_b64":"GZwt9ydH0IZ2rV+aLUB/ycWCuzbbdRWSMjvlfXnGwV1a4k5+aB788VxcSVw80gzY6aBiBl8Xog+eLeTCd3uXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e8e34927e2d77fe564affa84fd448e8fb11b2debdb3120f5db54cd92d8533f8","last_reissued_at":"2026-07-05T09:57:50.897009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:50.897009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.02964","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":"2026-07-05T09:57:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olhAj9quXcIUeMJD98cyx1Uiv0TNHyRVEQX0/89s8LZJPwnNu8eUIJ0MfKm/taFKMWmeZH9j5CRiEcxrcXeyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:43:03.841573Z"},"content_sha256":"86e85fcf37167a7d580691c48db88c8f0c9105ee30a1c86e71f1963c9d7471ff","schema_version":"1.0","event_id":"sha256:86e85fcf37167a7d580691c48db88c8f0c9105ee30a1c86e71f1963c9d7471ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N2HDJET6FV374VSK76UE7VCI5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changming Xiao, Changshui Zhang, Feng Zhou, Haodi Liu, Lin Chen, Qi Yang, Wanpeng Hu","submitted_at":"2025-01-06T12:16:56Z","abstract_excerpt":"Complex visual reasoning remains a key challenge today. Typically, the challenge is tackled using methodologies such as Chain of Thought (COT) and visual instruction tuning. However, how to organically combine these two methodologies for greater success remains unexplored. Also, issues like hallucinations and high training cost still need to be addressed. In this work, we devise an innovative multi-round training and reasoning framework suitable for lightweight Multimodal Large Language Models (MLLMs). Our self-questioning approach heuristically guides MLLMs to focus on visual clues relevant t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02964","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/2501.02964/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":"2026-07-05T09:57:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DsUwDRr7FU+GsKPXH4uI7SdRYzUaMBQVule6g4epZt31q1OYLN1LWaIYveBm4KgI3suNmwyIz/+nmsWpqz7YBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:43:03.842072Z"},"content_sha256":"5433c180a3cde69381f23eab0c69d21279d0bfbf9c9d1e1b8a168da773a01ff4","schema_version":"1.0","event_id":"sha256:5433c180a3cde69381f23eab0c69d21279d0bfbf9c9d1e1b8a168da773a01ff4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N2HDJET6FV374VSK76UE7VCI5D/bundle.json","state_url":"https://pith.science/pith/N2HDJET6FV374VSK76UE7VCI5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N2HDJET6FV374VSK76UE7VCI5D/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":"2026-08-08T18:43:03Z","links":{"resolver":"https://pith.science/pith/N2HDJET6FV374VSK76UE7VCI5D","bundle":"https://pith.science/pith/N2HDJET6FV374VSK76UE7VCI5D/bundle.json","state":"https://pith.science/pith/N2HDJET6FV374VSK76UE7VCI5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N2HDJET6FV374VSK76UE7VCI5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N2HDJET6FV374VSK76UE7VCI5D","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":"89e4ba227902b2ac35e26d030f60865c77b40a262671dd56f84a4a34fc3d81a4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T12:16:56Z","title_canon_sha256":"60238a67caa664d27c3a43e3db3f4dba52a8e858f1090907ddc67f1f9e209f4d"},"schema_version":"1.0","source":{"id":"2501.02964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02964","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02964v2","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02964","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_12","alias_value":"N2HDJET6FV37","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_16","alias_value":"N2HDJET6FV374VSK","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_8","alias_value":"N2HDJET6","created_at":"2026-07-05T09:57:50Z"}],"graph_snapshots":[{"event_id":"sha256:5433c180a3cde69381f23eab0c69d21279d0bfbf9c9d1e1b8a168da773a01ff4","target":"graph","created_at":"2026-07-05T09:57:50Z","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/2501.02964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Complex visual reasoning remains a key challenge today. Typically, the challenge is tackled using methodologies such as Chain of Thought (COT) and visual instruction tuning. However, how to organically combine these two methodologies for greater success remains unexplored. Also, issues like hallucinations and high training cost still need to be addressed. In this work, we devise an innovative multi-round training and reasoning framework suitable for lightweight Multimodal Large Language Models (MLLMs). Our self-questioning approach heuristically guides MLLMs to focus on visual clues relevant t","authors_text":"Changming Xiao, Changshui Zhang, Feng Zhou, Haodi Liu, Lin Chen, Qi Yang, Wanpeng Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T12:16:56Z","title":"Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02964","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":"sha256:86e85fcf37167a7d580691c48db88c8f0c9105ee30a1c86e71f1963c9d7471ff","target":"record","created_at":"2026-07-05T09:57:50Z","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":"89e4ba227902b2ac35e26d030f60865c77b40a262671dd56f84a4a34fc3d81a4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T12:16:56Z","title_canon_sha256":"60238a67caa664d27c3a43e3db3f4dba52a8e858f1090907ddc67f1f9e209f4d"},"schema_version":"1.0","source":{"id":"2501.02964","kind":"arxiv","version":2}},"canonical_sha256":"6e8e34927e2d77fe564affa84fd448e8fb11b2debdb3120f5db54cd92d8533f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e8e34927e2d77fe564affa84fd448e8fb11b2debdb3120f5db54cd92d8533f8","first_computed_at":"2026-07-05T09:57:50.897009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:50.897009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GZwt9ydH0IZ2rV+aLUB/ycWCuzbbdRWSMjvlfXnGwV1a4k5+aB788VxcSVw80gzY6aBiBl8Xog+eLeTCd3uXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:50.897473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86e85fcf37167a7d580691c48db88c8f0c9105ee30a1c86e71f1963c9d7471ff","sha256:5433c180a3cde69381f23eab0c69d21279d0bfbf9c9d1e1b8a168da773a01ff4"],"state_sha256":"76deb78e85dbb7654bee899c229521cdd7d192bb5bd6291c373f0b7af8ab813d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiAnanSnxAfAidogeNaC6eqSfRltTJaR3F2yLhTkkxnRqCdja6vsqwdt9Tb6Kz4ZHYLk36NvryHXiJGH5Io4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:43:03.847195Z","bundle_sha256":"9cb13381e751fe0e1eef73c12130cc0eee9c3e768bd123873b97909478282389"}}