{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4NPPWFDSH7M666K2EPYUXTCUYW","short_pith_number":"pith:4NPPWFDS","canonical_record":{"source":{"id":"2506.17218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0de502ca162d4f3dafd62f4e4c966d0cd99ddd23f6b77b505e00432c15ea88e","abstract_canon_sha256":"dae1cfd5ed21e534c7c869b9ad17b1dbd21cd28467b078177ac3e317c33e4410"},"schema_version":"1.0"},"canonical_sha256":"e35efb14723fd9ef795a23f14bcc54c58cd50bf6e7652cb810f728f00e33b9d5","source":{"kind":"arxiv","id":"2506.17218","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17218","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17218v1","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17218","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"4NPPWFDSH7M6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4NPPWFDSH7M666K2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4NPPWFDS","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4NPPWFDSH7M666K2EPYUXTCUYW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0de502ca162d4f3dafd62f4e4c966d0cd99ddd23f6b77b505e00432c15ea88e","abstract_canon_sha256":"dae1cfd5ed21e534c7c869b9ad17b1dbd21cd28467b078177ac3e317c33e4410"},"schema_version":"1.0"},"canonical_sha256":"e35efb14723fd9ef795a23f14bcc54c58cd50bf6e7652cb810f728f00e33b9d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.204908Z","signature_b64":"x9ZzK0HW9j1VtDb+cqTWAOyyKgw/uOWV9HaFJ3PVndjE67iFlS6HnU75eJhasuKd7oz9lIyMkwefpF0WwHsNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e35efb14723fd9ef795a23f14bcc54c58cd50bf6e7652cb810f728f00e33b9d5","last_reissued_at":"2026-05-17T23:38:47.203851Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.203851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17218","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":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zli6mkTE3abJMUhTdy3v0w6GRaZU3JvzYunuR9O2Brz+4TqKPJaXOwbvQCux1ZFgY/i3q9m4lUBaX2IXtxobBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T15:30:31.709243Z"},"content_sha256":"db5ac3296dae52b694dbe220f2cab771a6d84334154e0a95896689a026d827ea","schema_version":"1.0","event_id":"sha256:db5ac3296dae52b694dbe220f2cab771a6d84334154e0a95896689a026d827ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4NPPWFDSH7M666K2EPYUXTCUYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Delin Chen, Maohao Shen, Xueyang Yu, Zeyuan Yang","submitted_at":"2025-06-20T17:59:31Z","abstract_excerpt":"Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render explicit images, but the heavy image-generation pre-training often hinders the reasoning ability. Inspired by the way humans reason with mental imagery-the internal construction and manipulation of visual cues-we investigate whether VLMs can reason through interleaved multimodal trajectories without producing explicit images. To this end, we present a Machine Me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17218","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":""},"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":"2026-05-17T23:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tFdiSSMFRxL1BkLgCpcNfblr/JxaqEwaEva8sNcKqfsWu8gxkAuPytWJOj27aaLz+v+bTORs2aKb3WK+YiRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T15:30:31.709984Z"},"content_sha256":"b10539b1531a9c8d160f6fae0c3b02c5b198fce86e903385dc5482ca9c8a9b02","schema_version":"1.0","event_id":"sha256:b10539b1531a9c8d160f6fae0c3b02c5b198fce86e903385dc5482ca9c8a9b02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NPPWFDSH7M666K2EPYUXTCUYW/bundle.json","state_url":"https://pith.science/pith/4NPPWFDSH7M666K2EPYUXTCUYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NPPWFDSH7M666K2EPYUXTCUYW/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":"2026-05-24T15:30:31Z","links":{"resolver":"https://pith.science/pith/4NPPWFDSH7M666K2EPYUXTCUYW","bundle":"https://pith.science/pith/4NPPWFDSH7M666K2EPYUXTCUYW/bundle.json","state":"https://pith.science/pith/4NPPWFDSH7M666K2EPYUXTCUYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NPPWFDSH7M666K2EPYUXTCUYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4NPPWFDSH7M666K2EPYUXTCUYW","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":"dae1cfd5ed21e534c7c869b9ad17b1dbd21cd28467b078177ac3e317c33e4410","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:31Z","title_canon_sha256":"e0de502ca162d4f3dafd62f4e4c966d0cd99ddd23f6b77b505e00432c15ea88e"},"schema_version":"1.0","source":{"id":"2506.17218","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17218","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17218v1","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17218","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"4NPPWFDSH7M6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4NPPWFDSH7M666K2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4NPPWFDS","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b10539b1531a9c8d160f6fae0c3b02c5b198fce86e903385dc5482ca9c8a9b02","target":"graph","created_at":"2026-05-17T23:38:47Z","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"},"paper":{"abstract_excerpt":"Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render explicit images, but the heavy image-generation pre-training often hinders the reasoning ability. Inspired by the way humans reason with mental imagery-the internal construction and manipulation of visual cues-we investigate whether VLMs can reason through interleaved multimodal trajectories without producing explicit images. To this end, we present a Machine Me","authors_text":"Chuang Gan, Delin Chen, Maohao Shen, Xueyang Yu, Zeyuan Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:31Z","title":"Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17218","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:db5ac3296dae52b694dbe220f2cab771a6d84334154e0a95896689a026d827ea","target":"record","created_at":"2026-05-17T23:38:47Z","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":"dae1cfd5ed21e534c7c869b9ad17b1dbd21cd28467b078177ac3e317c33e4410","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:31Z","title_canon_sha256":"e0de502ca162d4f3dafd62f4e4c966d0cd99ddd23f6b77b505e00432c15ea88e"},"schema_version":"1.0","source":{"id":"2506.17218","kind":"arxiv","version":1}},"canonical_sha256":"e35efb14723fd9ef795a23f14bcc54c58cd50bf6e7652cb810f728f00e33b9d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e35efb14723fd9ef795a23f14bcc54c58cd50bf6e7652cb810f728f00e33b9d5","first_computed_at":"2026-05-17T23:38:47.203851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.203851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x9ZzK0HW9j1VtDb+cqTWAOyyKgw/uOWV9HaFJ3PVndjE67iFlS6HnU75eJhasuKd7oz9lIyMkwefpF0WwHsNBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.204908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17218","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db5ac3296dae52b694dbe220f2cab771a6d84334154e0a95896689a026d827ea","sha256:b10539b1531a9c8d160f6fae0c3b02c5b198fce86e903385dc5482ca9c8a9b02"],"state_sha256":"0628d23e7cca8684fd666afd8111f3d97e77b57f4cf3c1038e9bbdeb5ab4dcf5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ve2hcDhMlGQ0kvmoh04FKAwdoq+ohe4LDKBTUCmhRrF3PU9LVdm/bSbZFPMIFw3NQJJHC5ZB9uHb7bhwM5NyBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T15:30:31.713616Z","bundle_sha256":"bccdf7be730736b0878a6e362c899e2be1660939244a93ada97d9f95e7d6b3f8"}}