{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZC2JPTMDYODK4M6FD3G22BMA7B","short_pith_number":"pith:ZC2JPTMD","canonical_record":{"source":{"id":"2603.12252","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T17:58:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e68e7f50a0979973dea633bbecf9cb222adc372e463d5a4cdbd2ef484515afe1","abstract_canon_sha256":"c58348ca91fa7b017350d9704b4864759c788dc0ed0b44d13c91a6bf7001a204"},"schema_version":"1.0"},"canonical_sha256":"c8b497cd83c386ae33c51ecdad0580f879c5cf7949430ef32cf3dac79f1c3913","source":{"kind":"arxiv","id":"2603.12252","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.12252","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2603.12252v4","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12252","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZC2JPTMDYODK","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZC2JPTMDYODK4M6F","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZC2JPTMD","created_at":"2026-06-19T16:12:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZC2JPTMDYODK4M6FD3G22BMA7B","target":"record","payload":{"canonical_record":{"source":{"id":"2603.12252","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T17:58:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e68e7f50a0979973dea633bbecf9cb222adc372e463d5a4cdbd2ef484515afe1","abstract_canon_sha256":"c58348ca91fa7b017350d9704b4864759c788dc0ed0b44d13c91a6bf7001a204"},"schema_version":"1.0"},"canonical_sha256":"c8b497cd83c386ae33c51ecdad0580f879c5cf7949430ef32cf3dac79f1c3913","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:19.502201Z","signature_b64":"2Pb1eVONMypMUAHNWzXZ01geklfUfaswa6Qh6+EzOtiZ837E//lIRRP2NEhnYrU8H5WzGRuEdwAFlQJN7nPwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8b497cd83c386ae33c51ecdad0580f879c5cf7949430ef32cf3dac79f1c3913","last_reissued_at":"2026-06-19T16:12:19.501780Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:19.501780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.12252","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnQLpci14PA3rdpMB5aE8UmZ/lyD3HXLePwuhFhPbyjaBoV1tOp4BoNtrAZVarhLB7u0Z7jeyaV4sX4Az0EZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:06:36.155719Z"},"content_sha256":"ee05aa014fbd119189c0a5c61e7904239d07941046a7d2edee795892bb7d3da5","schema_version":"1.0","event_id":"sha256:ee05aa014fbd119189c0a5c61e7904239d07941046a7d2edee795892bb7d3da5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZC2JPTMDYODK4M6FD3G22BMA7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Beichen Zhang, Jiazi Bu, Kai Chen, Long Xing, Xilin Wei, Xuanlang Dai, Yuhang Zang, Yuhong Liu, Yujie Zhou","submitted_at":"2026-03-12T17:58:48Z","abstract_excerpt":"Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12252","kind":"arxiv","version":4},"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/2603.12252/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":"2026-06-19T16:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cFMMooqlQuCPf4nJeqfFbPK9pTTaC8YDzHJWE6CAbwmzAFxLPfirRuZDsUhArY71+Cjl275ed5faeUAWa8JnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:06:36.156271Z"},"content_sha256":"3e2e38d9bacab59413d44c6a0efab34914089a08794c5e710519263c4cc31987","schema_version":"1.0","event_id":"sha256:3e2e38d9bacab59413d44c6a0efab34914089a08794c5e710519263c4cc31987"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZC2JPTMDYODK4M6FD3G22BMA7B/bundle.json","state_url":"https://pith.science/pith/ZC2JPTMDYODK4M6FD3G22BMA7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZC2JPTMDYODK4M6FD3G22BMA7B/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":"2026-07-05T09:06:36Z","links":{"resolver":"https://pith.science/pith/ZC2JPTMDYODK4M6FD3G22BMA7B","bundle":"https://pith.science/pith/ZC2JPTMDYODK4M6FD3G22BMA7B/bundle.json","state":"https://pith.science/pith/ZC2JPTMDYODK4M6FD3G22BMA7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZC2JPTMDYODK4M6FD3G22BMA7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZC2JPTMDYODK4M6FD3G22BMA7B","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":"c58348ca91fa7b017350d9704b4864759c788dc0ed0b44d13c91a6bf7001a204","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T17:58:48Z","title_canon_sha256":"e68e7f50a0979973dea633bbecf9cb222adc372e463d5a4cdbd2ef484515afe1"},"schema_version":"1.0","source":{"id":"2603.12252","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.12252","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2603.12252v4","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12252","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZC2JPTMDYODK","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZC2JPTMDYODK4M6F","created_at":"2026-06-19T16:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZC2JPTMD","created_at":"2026-06-19T16:12:19Z"}],"graph_snapshots":[{"event_id":"sha256:3e2e38d9bacab59413d44c6a0efab34914089a08794c5e710519263c4cc31987","target":"graph","created_at":"2026-06-19T16:12:19Z","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/2603.12252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing com","authors_text":"Beichen Zhang, Jiazi Bu, Kai Chen, Long Xing, Xilin Wei, Xuanlang Dai, Yuhang Zang, Yuhong Liu, Yujie Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T17:58:48Z","title":"EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12252","kind":"arxiv","version":4},"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:ee05aa014fbd119189c0a5c61e7904239d07941046a7d2edee795892bb7d3da5","target":"record","created_at":"2026-06-19T16:12:19Z","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":"c58348ca91fa7b017350d9704b4864759c788dc0ed0b44d13c91a6bf7001a204","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-12T17:58:48Z","title_canon_sha256":"e68e7f50a0979973dea633bbecf9cb222adc372e463d5a4cdbd2ef484515afe1"},"schema_version":"1.0","source":{"id":"2603.12252","kind":"arxiv","version":4}},"canonical_sha256":"c8b497cd83c386ae33c51ecdad0580f879c5cf7949430ef32cf3dac79f1c3913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8b497cd83c386ae33c51ecdad0580f879c5cf7949430ef32cf3dac79f1c3913","first_computed_at":"2026-06-19T16:12:19.501780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:19.501780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Pb1eVONMypMUAHNWzXZ01geklfUfaswa6Qh6+EzOtiZ837E//lIRRP2NEhnYrU8H5WzGRuEdwAFlQJN7nPwDg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:19.502201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.12252","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee05aa014fbd119189c0a5c61e7904239d07941046a7d2edee795892bb7d3da5","sha256:3e2e38d9bacab59413d44c6a0efab34914089a08794c5e710519263c4cc31987"],"state_sha256":"575a9efbb463fbad69e1d211540120ad186ecbd66c2cbc2109842c139ab266fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SxSykkvrmHeELmJNArpkyBxA07gUbf4oe8OWpZd8p12p7kJIQagndg3K1f3HXroczrgh8SiCRkFR4/LXF+z8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:06:36.158522Z","bundle_sha256":"ecfafaf306956a73e880f5939ef845fd71389f941fe710d15b36b6cbd87dafd0"}}