{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PKWXCOSB2FJWJCHI2DWZLJMAJQ","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":"6d501dcb2c2474754c0e501fd55b15b38cf1f6811b9ec6403d3c62f2fcae4837","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T16:12:45Z","title_canon_sha256":"ff8d5e6e30fb05c1cf5b03b39ee23bbc63994681644f396bf4506f6a48416b24"},"schema_version":"1.0","source":{"id":"2505.22525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22525","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22525v1","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22525","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"PKWXCOSB2FJW","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"PKWXCOSB2FJWJCHI","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"PKWXCOSB","created_at":"2026-07-05T11:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:df6d15080ecbb72f70c13f13be4a208b1508dc199c4ee45bd9c71fa020859781","target":"graph","created_at":"2026-07-05T11:11:26Z","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/2505.22525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through spontaneous generation of intermediate visual thinking steps. Current visual reasoning with LMMs is constrained to either processing fixed user-provided images or reasoning solely through text-based chain-of-thought (CoT). Thinking with Generated Images unlocks a new dimension of cognitive capability where models can actively construct intermediate visual thoughts, c","authors_text":"Ethan Chern, Jiadi Su, Pengfei Liu, Siqi Kou, Steffi Chern, Yan Ma, Zhijie Deng, Zhulin Hu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T16:12:45Z","title":"Thinking with Generated Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22525","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":"sha256:2e02ebd2268aa00cd3edc703b846b4ab808ff396de83e499a735316e9aa4224d","target":"record","created_at":"2026-07-05T11:11:26Z","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":"6d501dcb2c2474754c0e501fd55b15b38cf1f6811b9ec6403d3c62f2fcae4837","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T16:12:45Z","title_canon_sha256":"ff8d5e6e30fb05c1cf5b03b39ee23bbc63994681644f396bf4506f6a48416b24"},"schema_version":"1.0","source":{"id":"2505.22525","kind":"arxiv","version":1}},"canonical_sha256":"7aad713a41d1536488e8d0ed95a5804c3d13af1ea733d5ff650ffa9e487853a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7aad713a41d1536488e8d0ed95a5804c3d13af1ea733d5ff650ffa9e487853a7","first_computed_at":"2026-07-05T11:11:26.030623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:26.030623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OdOn4KGcSeYOoT4O0E9JeTGaFfZCofn1LdoHRumWqn1UKBQ8PQQ54As0Tr0P+UQlJoB7fQbF2vFcUnBfCqo2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:26.031133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e02ebd2268aa00cd3edc703b846b4ab808ff396de83e499a735316e9aa4224d","sha256:df6d15080ecbb72f70c13f13be4a208b1508dc199c4ee45bd9c71fa020859781"],"state_sha256":"44a02f3140038a04eca6e597aba54a4fdf59dbc17fb08b0992890b5d700f49b2"}