{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4GETQN3LW5FXTG7XHGV66TQJCC","short_pith_number":"pith:4GETQN3L","canonical_record":{"source":{"id":"2512.21218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T14:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"8a80afb1648ea5700fff51b91d2e3239c06a338761ade10e22d671544d9aedd8","abstract_canon_sha256":"5cdd7ff354060d90293ef302417c89af4f9e53cb62926bf269fd47c1303591d9"},"schema_version":"1.0"},"canonical_sha256":"e18938376bb74b799bf739abef4e09108cfeabc94093784c0af5d9396b8ceb0d","source":{"kind":"arxiv","id":"2512.21218","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.21218","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2512.21218v2","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21218","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"4GETQN3LW5FX","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"4GETQN3LW5FXTG7X","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"4GETQN3L","created_at":"2026-06-05T00:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4GETQN3LW5FXTG7XHGV66TQJCC","target":"record","payload":{"canonical_record":{"source":{"id":"2512.21218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T14:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"8a80afb1648ea5700fff51b91d2e3239c06a338761ade10e22d671544d9aedd8","abstract_canon_sha256":"5cdd7ff354060d90293ef302417c89af4f9e53cb62926bf269fd47c1303591d9"},"schema_version":"1.0"},"canonical_sha256":"e18938376bb74b799bf739abef4e09108cfeabc94093784c0af5d9396b8ceb0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:44.946108Z","signature_b64":"jYERyqs+Tu4UYTMG+jjCsugZaDv0oWF3ovstyLaT2lhAxMLPZ0+XvQ1ENAtJ97C7oew5xq35Zh88ZUuR6enLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e18938376bb74b799bf739abef4e09108cfeabc94093784c0af5d9396b8ceb0d","last_reissued_at":"2026-06-05T00:13:44.945494Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:44.945494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.21218","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2gXeEeq7sWpBA97/3rUC5iyuspkUDj5P/aTaAEjgCOFMDFLkiZyq4jHQ4sryE611odQZyt7s+nliaaVMDMACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T05:37:36.735093Z"},"content_sha256":"3227354302cb68c9d790f62033d5cb28c183331b873c125e8c70a06aa3f803af","schema_version":"1.0","event_id":"sha256:3227354302cb68c9d790f62033d5cb28c183331b873c125e8c70a06aa3f803af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4GETQN3LW5FXTG7XHGV66TQJCC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Implicit Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuyi Shang, Kelvin Li, Leonid Karlinsky, Roei Herzig, Rogerio Feris, Trevor Darrell","submitted_at":"2025-12-24T14:59:49Z","abstract_excerpt":"While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are predominantly visual. Recent approaches have sought to address this by supervising intermediate visual steps with helper images, depth maps, or image crops. However, these strategies impose restrictive priors on what \"useful\" visual abstractions look like, add heavy annotation costs, and struggle to generalize across tasks. To address this critical limitation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.21218","kind":"arxiv","version":2},"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/2512.21218/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":"2026-06-05T00:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APEg5nGsz9ArdmzGX9GVTagINn6mUK9jS5u54XIIxIaAiNwGB4pz3CC8eKvux4uT2kaG8X/iLsd5HwirddUADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T05:37:36.735895Z"},"content_sha256":"f0884e081d6d2d881e5db95416b62c352f4d7eefbbaa76b1dd93b7f2877e5afb","schema_version":"1.0","event_id":"sha256:f0884e081d6d2d881e5db95416b62c352f4d7eefbbaa76b1dd93b7f2877e5afb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4GETQN3LW5FXTG7XHGV66TQJCC/bundle.json","state_url":"https://pith.science/pith/4GETQN3LW5FXTG7XHGV66TQJCC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4GETQN3LW5FXTG7XHGV66TQJCC/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":"2026-06-10T05:37:36Z","links":{"resolver":"https://pith.science/pith/4GETQN3LW5FXTG7XHGV66TQJCC","bundle":"https://pith.science/pith/4GETQN3LW5FXTG7XHGV66TQJCC/bundle.json","state":"https://pith.science/pith/4GETQN3LW5FXTG7XHGV66TQJCC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4GETQN3LW5FXTG7XHGV66TQJCC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4GETQN3LW5FXTG7XHGV66TQJCC","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":"5cdd7ff354060d90293ef302417c89af4f9e53cb62926bf269fd47c1303591d9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T14:59:49Z","title_canon_sha256":"8a80afb1648ea5700fff51b91d2e3239c06a338761ade10e22d671544d9aedd8"},"schema_version":"1.0","source":{"id":"2512.21218","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.21218","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2512.21218v2","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21218","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"4GETQN3LW5FX","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"4GETQN3LW5FXTG7X","created_at":"2026-06-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"4GETQN3L","created_at":"2026-06-05T00:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:f0884e081d6d2d881e5db95416b62c352f4d7eefbbaa76b1dd93b7f2877e5afb","target":"graph","created_at":"2026-06-05T00:13:44Z","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/2512.21218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are predominantly visual. Recent approaches have sought to address this by supervising intermediate visual steps with helper images, depth maps, or image crops. However, these strategies impose restrictive priors on what \"useful\" visual abstractions look like, add heavy annotation costs, and struggle to generalize across tasks. To address this critical limitation","authors_text":"Chuyi Shang, Kelvin Li, Leonid Karlinsky, Roei Herzig, Rogerio Feris, Trevor Darrell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T14:59:49Z","title":"Latent Implicit Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.21218","kind":"arxiv","version":2},"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":"sha256:3227354302cb68c9d790f62033d5cb28c183331b873c125e8c70a06aa3f803af","target":"record","created_at":"2026-06-05T00:13:44Z","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":"5cdd7ff354060d90293ef302417c89af4f9e53cb62926bf269fd47c1303591d9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T14:59:49Z","title_canon_sha256":"8a80afb1648ea5700fff51b91d2e3239c06a338761ade10e22d671544d9aedd8"},"schema_version":"1.0","source":{"id":"2512.21218","kind":"arxiv","version":2}},"canonical_sha256":"e18938376bb74b799bf739abef4e09108cfeabc94093784c0af5d9396b8ceb0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e18938376bb74b799bf739abef4e09108cfeabc94093784c0af5d9396b8ceb0d","first_computed_at":"2026-06-05T00:13:44.945494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:44.945494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jYERyqs+Tu4UYTMG+jjCsugZaDv0oWF3ovstyLaT2lhAxMLPZ0+XvQ1ENAtJ97C7oew5xq35Zh88ZUuR6enLCw==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:44.946108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.21218","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3227354302cb68c9d790f62033d5cb28c183331b873c125e8c70a06aa3f803af","sha256:f0884e081d6d2d881e5db95416b62c352f4d7eefbbaa76b1dd93b7f2877e5afb"],"state_sha256":"f61d2ac033d012b3628c7fc02feb3af9e7504bd7081faf4143eb36c32018102b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yBI+L0VbctGIQKIMy4ZiOTDrDijcsVfXhPx8/MmzxViAI42UTIWjAOBC33Xi9aZVMZ2bI0W7FLT+UT+DwxMzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T05:37:36.740305Z","bundle_sha256":"3f2175e58578c69dec6518d3a3b57a295bea517c820a2fb4ed7a2b7b6d827b8b"}}