{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PVOEXWVC3LPNZSVJ65R7NOSV3H","short_pith_number":"pith:PVOEXWVC","canonical_record":{"source":{"id":"2606.31986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"f19bfdc373b421eb1211a255115f59abfe56b9c88b1898ac82217844f72a484e","abstract_canon_sha256":"a49533e425f25857a61c22d9f35653f84af38c2f03ac2613bb9d1be9c838d976"},"schema_version":"1.0"},"canonical_sha256":"7d5c4bdaa2dadedccaa9f763f6ba55d9dd9affe691f2047cd06427dd5266d7b8","source":{"kind":"arxiv","id":"2606.31986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31986","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31986v1","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31986","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"PVOEXWVC3LPN","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"PVOEXWVC3LPNZSVJ","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"PVOEXWVC","created_at":"2026-07-01T01:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PVOEXWVC3LPNZSVJ65R7NOSV3H","target":"record","payload":{"canonical_record":{"source":{"id":"2606.31986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"f19bfdc373b421eb1211a255115f59abfe56b9c88b1898ac82217844f72a484e","abstract_canon_sha256":"a49533e425f25857a61c22d9f35653f84af38c2f03ac2613bb9d1be9c838d976"},"schema_version":"1.0"},"canonical_sha256":"7d5c4bdaa2dadedccaa9f763f6ba55d9dd9affe691f2047cd06427dd5266d7b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:28.257893Z","signature_b64":"qCP3EzLLlx7fgi1RSKv3nVgFK1ztmsqu45GGILX9pjs/p0nP6ykVpq6bbUXk0ctzIks9R56eiP8/5IFzLj+cDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d5c4bdaa2dadedccaa9f763f6ba55d9dd9affe691f2047cd06427dd5266d7b8","last_reissued_at":"2026-07-01T01:18:28.257376Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:28.257376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.31986","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":"2026-07-01T01:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xb3Kav9e98ydSg5WZ4aMd3Yyur3UA4cGorw+wucz3PneqglF18kHWQtn4AdH9OWnps2vAUx8OaKan6839+9MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T23:28:17.199867Z"},"content_sha256":"b1d7072bd18d8bc2ada624e5860607c7f55b836edb4e0dae9d855c096433a6de","schema_version":"1.0","event_id":"sha256:b1d7072bd18d8bc2ada624e5860607c7f55b836edb4e0dae9d855c096433a6de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PVOEXWVC3LPNZSVJ65R7NOSV3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Wan, Lianyu Hu, Qing Guo, Shengqian Qin, Wei Feng, Yang Liu, Zeqin Liao","submitted_at":"2026-06-30T17:24:40Z","abstract_excerpt":"Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit intermediate reasoning steps in natural language. However, this text-based reasoning paradigm is inherently slow at inference time with even thousands of tokens and fundamentally constrained by the expressiveness of natural language. In this paper, we propose CoLT, (Chain of Latent Thoughts), a novel framework that teaches multi-modal models to reason through a chain of latent thought representations instead of verbose text tokens, which can per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31986","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/2606.31986/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":"2026-07-01T01:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCjcf/rZHmzHlxOyJ8/1s920d9wL5wfhle6uno52sA7rQamGigAFWw2nDaNBvSR/zk78VBxoWV/szTZoU9kBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T23:28:17.200490Z"},"content_sha256":"aa94e3a1f2d9afae72cdcc17d8c947046c29f6b9154dd08ce9def9694f841d38","schema_version":"1.0","event_id":"sha256:aa94e3a1f2d9afae72cdcc17d8c947046c29f6b9154dd08ce9def9694f841d38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H/bundle.json","state_url":"https://pith.science/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H/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":"2026-07-01T23:28:17Z","links":{"resolver":"https://pith.science/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H","bundle":"https://pith.science/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H/bundle.json","state":"https://pith.science/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PVOEXWVC3LPNZSVJ65R7NOSV3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PVOEXWVC3LPNZSVJ65R7NOSV3H","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":"a49533e425f25857a61c22d9f35653f84af38c2f03ac2613bb9d1be9c838d976","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:24:40Z","title_canon_sha256":"f19bfdc373b421eb1211a255115f59abfe56b9c88b1898ac82217844f72a484e"},"schema_version":"1.0","source":{"id":"2606.31986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31986","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31986v1","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31986","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"PVOEXWVC3LPN","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"PVOEXWVC3LPNZSVJ","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"PVOEXWVC","created_at":"2026-07-01T01:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:aa94e3a1f2d9afae72cdcc17d8c947046c29f6b9154dd08ce9def9694f841d38","target":"graph","created_at":"2026-07-01T01:18:28Z","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/2606.31986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit intermediate reasoning steps in natural language. However, this text-based reasoning paradigm is inherently slow at inference time with even thousands of tokens and fundamentally constrained by the expressiveness of natural language. In this paper, we propose CoLT, (Chain of Latent Thoughts), a novel framework that teaches multi-modal models to reason through a chain of latent thought representations instead of verbose text tokens, which can per","authors_text":"Liang Wan, Lianyu Hu, Qing Guo, Shengqian Qin, Wei Feng, Yang Liu, Zeqin Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:24:40Z","title":"CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31986","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:b1d7072bd18d8bc2ada624e5860607c7f55b836edb4e0dae9d855c096433a6de","target":"record","created_at":"2026-07-01T01:18:28Z","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":"a49533e425f25857a61c22d9f35653f84af38c2f03ac2613bb9d1be9c838d976","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T17:24:40Z","title_canon_sha256":"f19bfdc373b421eb1211a255115f59abfe56b9c88b1898ac82217844f72a484e"},"schema_version":"1.0","source":{"id":"2606.31986","kind":"arxiv","version":1}},"canonical_sha256":"7d5c4bdaa2dadedccaa9f763f6ba55d9dd9affe691f2047cd06427dd5266d7b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d5c4bdaa2dadedccaa9f763f6ba55d9dd9affe691f2047cd06427dd5266d7b8","first_computed_at":"2026-07-01T01:18:28.257376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:28.257376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qCP3EzLLlx7fgi1RSKv3nVgFK1ztmsqu45GGILX9pjs/p0nP6ykVpq6bbUXk0ctzIks9R56eiP8/5IFzLj+cDg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:28.257893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1d7072bd18d8bc2ada624e5860607c7f55b836edb4e0dae9d855c096433a6de","sha256:aa94e3a1f2d9afae72cdcc17d8c947046c29f6b9154dd08ce9def9694f841d38"],"state_sha256":"6e1b3a000242b8a71199d0f2d1d5b326f1719203af53034058d3ae07a43ad8a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QepTrRpHshctBTjZeeGUEPGicWDIUjrB3Aj90+X4KNuwyBoVObuakD4biKgjmi1mW0cRGL1hijDGgFibpvYqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T23:28:17.204060Z","bundle_sha256":"75a8832438cc7c8afd9736acbfc63fda70e80c1b66d7b5ac50191c6a486ae869"}}