{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3FMZOXYOMFQC6QY6A33QJHMINR","short_pith_number":"pith:3FMZOXYO","canonical_record":{"source":{"id":"2410.16198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T17:00:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d934249d37ddfb92185e410423c844d24530d4628b00cec809d889109cfae1e5","abstract_canon_sha256":"7bf2f467772a1b249a5f4e5803af3859064fba2ce70f3948809d153cc1279e15"},"schema_version":"1.0"},"canonical_sha256":"d959975f0e61602f431e06f7049d886c66d725e80dff9516c26cbfd765bc49be","source":{"kind":"arxiv","id":"2410.16198","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16198","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16198v1","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16198","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"3FMZOXYOMFQC","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"3FMZOXYOMFQC6QY6","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"3FMZOXYO","created_at":"2026-07-05T09:23:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3FMZOXYOMFQC6QY6A33QJHMINR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T17:00:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d934249d37ddfb92185e410423c844d24530d4628b00cec809d889109cfae1e5","abstract_canon_sha256":"7bf2f467772a1b249a5f4e5803af3859064fba2ce70f3948809d153cc1279e15"},"schema_version":"1.0"},"canonical_sha256":"d959975f0e61602f431e06f7049d886c66d725e80dff9516c26cbfd765bc49be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:31.267960Z","signature_b64":"JfDAZeplDde6uydyVW69lBh1Vu/43B8ArCNz8Nwq3w/ofVa1NxmH0LcnzD7lWCXiZWC5RnD2dbsh2my8VsqvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d959975f0e61602f431e06f7049d886c66d725e80dff9516c26cbfd765bc49be","last_reissued_at":"2026-07-05T09:23:31.267436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:31.267436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16198","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":"2026-07-05T09:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIAXW9bbT6vSrNaphFdI2cR5lIcsoUYphDXJdBVpolPLJXGVdZuzsxH6HBIhxlFTxi4StkDyWF9ESDV8mpTfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:10:11.079738Z"},"content_sha256":"bb2063919a45818b954ad8db40dd925528a7286d18ff46c7c8210f14710478c4","schema_version":"1.0","event_id":"sha256:bb2063919a45818b954ad8db40dd925528a7286d18ff46c7c8210f14710478c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3FMZOXYOMFQC6QY6A33QJHMINR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improve Vision Language Model Chain-of-thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Bowen Zhang, Haotian Zhang, Ruohong Zhang, Ruoming Pang, Yanghao Li, Yiming Yang, Yinfei Yang, Zhe Gan, Zhiqing Sun","submitted_at":"2024-10-21T17:00:06Z","abstract_excerpt":"Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses. To address this, we propose a two-fold approach. First, we distill rationales from GPT-4o model to enrich the training data and fine-tune VLMs, boosting their CoT performance. Second, we app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16198","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/2410.16198/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":"2026-07-05T09:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8IkltJOr882Nxm6SGaogfPfykvzz3gMpnTxNk5EZHyjq2TW5KJE4JGAIdcd4kk0L9auAEJsCgTnFpBs0h2mDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:10:11.080234Z"},"content_sha256":"276b4b0fdb47805e77b5839255a770195b32eb9e0c8efd309d4be97400b92f7c","schema_version":"1.0","event_id":"sha256:276b4b0fdb47805e77b5839255a770195b32eb9e0c8efd309d4be97400b92f7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FMZOXYOMFQC6QY6A33QJHMINR/bundle.json","state_url":"https://pith.science/pith/3FMZOXYOMFQC6QY6A33QJHMINR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FMZOXYOMFQC6QY6A33QJHMINR/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":"2026-08-01T05:10:11Z","links":{"resolver":"https://pith.science/pith/3FMZOXYOMFQC6QY6A33QJHMINR","bundle":"https://pith.science/pith/3FMZOXYOMFQC6QY6A33QJHMINR/bundle.json","state":"https://pith.science/pith/3FMZOXYOMFQC6QY6A33QJHMINR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FMZOXYOMFQC6QY6A33QJHMINR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3FMZOXYOMFQC6QY6A33QJHMINR","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":"7bf2f467772a1b249a5f4e5803af3859064fba2ce70f3948809d153cc1279e15","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T17:00:06Z","title_canon_sha256":"d934249d37ddfb92185e410423c844d24530d4628b00cec809d889109cfae1e5"},"schema_version":"1.0","source":{"id":"2410.16198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16198","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16198v1","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16198","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"3FMZOXYOMFQC","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"3FMZOXYOMFQC6QY6","created_at":"2026-07-05T09:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"3FMZOXYO","created_at":"2026-07-05T09:23:31Z"}],"graph_snapshots":[{"event_id":"sha256:276b4b0fdb47805e77b5839255a770195b32eb9e0c8efd309d4be97400b92f7c","target":"graph","created_at":"2026-07-05T09:23:31Z","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/2410.16198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses. To address this, we propose a two-fold approach. First, we distill rationales from GPT-4o model to enrich the training data and fine-tune VLMs, boosting their CoT performance. Second, we app","authors_text":"Bowen Zhang, Haotian Zhang, Ruohong Zhang, Ruoming Pang, Yanghao Li, Yiming Yang, Yinfei Yang, Zhe Gan, Zhiqing Sun","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T17:00:06Z","title":"Improve Vision Language Model Chain-of-thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16198","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:bb2063919a45818b954ad8db40dd925528a7286d18ff46c7c8210f14710478c4","target":"record","created_at":"2026-07-05T09:23:31Z","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":"7bf2f467772a1b249a5f4e5803af3859064fba2ce70f3948809d153cc1279e15","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T17:00:06Z","title_canon_sha256":"d934249d37ddfb92185e410423c844d24530d4628b00cec809d889109cfae1e5"},"schema_version":"1.0","source":{"id":"2410.16198","kind":"arxiv","version":1}},"canonical_sha256":"d959975f0e61602f431e06f7049d886c66d725e80dff9516c26cbfd765bc49be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d959975f0e61602f431e06f7049d886c66d725e80dff9516c26cbfd765bc49be","first_computed_at":"2026-07-05T09:23:31.267436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:31.267436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JfDAZeplDde6uydyVW69lBh1Vu/43B8ArCNz8Nwq3w/ofVa1NxmH0LcnzD7lWCXiZWC5RnD2dbsh2my8VsqvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:31.267960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb2063919a45818b954ad8db40dd925528a7286d18ff46c7c8210f14710478c4","sha256:276b4b0fdb47805e77b5839255a770195b32eb9e0c8efd309d4be97400b92f7c"],"state_sha256":"fe70c638061d42439150ae36b64d70f166abc4af5d36bf4fc00d515d4fc70c14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+9di6GCyCWgzAKJZD612L5k1xrtiVyKOTZ3x75KBr0zNsUOBenk0YY5ZlHSIONpo0oBhxx+vLUxUdVAXo0bCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:10:11.083851Z","bundle_sha256":"81eb594dfed5f80504635eb87b4e8c9aa6dcd61e91edf6a6edd9658da73c204b"}}