{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7H4MTP642SB4IUNXFQRACI5RRR","short_pith_number":"pith:7H4MTP64","canonical_record":{"source":{"id":"2511.19418","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:55:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b22c500b98bf270bcb429c3753e1f5863b3e58e6acf4809f841553aadc3af9a","abstract_canon_sha256":"52a3f0f015a9efc287172c18a2b6a231b5367f635f9158337a88b45adec3b576"},"schema_version":"1.0"},"canonical_sha256":"f9f8c9bfdcd483c451b72c220123b18c6159bcf9ac6d5c5c2d90e481de74895a","source":{"kind":"arxiv","id":"2511.19418","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19418","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19418v3","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19418","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"7H4MTP642SB4","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"7H4MTP642SB4IUNX","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"7H4MTP64","created_at":"2026-08-06T01:16:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7H4MTP642SB4IUNXFQRACI5RRR","target":"record","payload":{"canonical_record":{"source":{"id":"2511.19418","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:55:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b22c500b98bf270bcb429c3753e1f5863b3e58e6acf4809f841553aadc3af9a","abstract_canon_sha256":"52a3f0f015a9efc287172c18a2b6a231b5367f635f9158337a88b45adec3b576"},"schema_version":"1.0"},"canonical_sha256":"f9f8c9bfdcd483c451b72c220123b18c6159bcf9ac6d5c5c2d90e481de74895a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:16:45.445328Z","signature_b64":"5CVXEWR6LjkDcftnbGtrA8i72+GV4T1HVd06UITrDobZg+uOSLkdaoshxVkwmChVV9xMgUgKfoTwdelwjHEJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f8c9bfdcd483c451b72c220123b18c6159bcf9ac6d5c5c2d90e481de74895a","last_reissued_at":"2026-08-06T01:16:45.443571Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:16:45.443571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.19418","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uGCELPxowIJo1cf8BKwhx7VjMlTD82DM3zpJDZ2Lz3LPbfMrFK6TVt/62wLojHIAkr3O+Op2jnVUHVl//CcKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:11:55.831888Z"},"content_sha256":"9e36862d78e45689c85b70bd236760faa5d64081665facfac7f019d66adc5c64","schema_version":"1.0","event_id":"sha256:9e36862d78e45689c85b70bd236760faa5d64081665facfac7f019d66adc5c64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7H4MTP642SB4IUNXFQRACI5RRR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bomin wei, Jiaxin Ge, Konstantinos Kallidromitis, Stephanie Fu, Trevor Darrell, Xudong Wang, Yiming Qin","submitted_at":"2025-11-24T18:55:19Z","abstract_excerpt":"Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that current VLMs have limited mechanisms to capture dense visual information across spatial dimensions. We introduce Chain-of-Visual-Thought (COVT), a framework that enables VLMs to reason not only in words but also through continuous visual tokens-compact latent representations that encode rich perceptual cues. Within a small budget of roughly 20 tokens, COVT "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19418","kind":"arxiv","version":3},"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/2511.19418/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":"2026-08-06T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vpckT7/JrGGphP8HS8NI4q18pA8PVX2AZuB3GWiEzUtZ0TYOit/24O1u51vRkb4U7PKzfAevdEUf7Sl5MjOZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:11:55.832414Z"},"content_sha256":"73249f7ff658ca687b9f367db75161396bf8728dc8a7007222eb3ce0e6abd9d5","schema_version":"1.0","event_id":"sha256:73249f7ff658ca687b9f367db75161396bf8728dc8a7007222eb3ce0e6abd9d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7H4MTP642SB4IUNXFQRACI5RRR/bundle.json","state_url":"https://pith.science/pith/7H4MTP642SB4IUNXFQRACI5RRR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7H4MTP642SB4IUNXFQRACI5RRR/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":"2026-08-07T06:11:55Z","links":{"resolver":"https://pith.science/pith/7H4MTP642SB4IUNXFQRACI5RRR","bundle":"https://pith.science/pith/7H4MTP642SB4IUNXFQRACI5RRR/bundle.json","state":"https://pith.science/pith/7H4MTP642SB4IUNXFQRACI5RRR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7H4MTP642SB4IUNXFQRACI5RRR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7H4MTP642SB4IUNXFQRACI5RRR","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":"52a3f0f015a9efc287172c18a2b6a231b5367f635f9158337a88b45adec3b576","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:55:19Z","title_canon_sha256":"9b22c500b98bf270bcb429c3753e1f5863b3e58e6acf4809f841553aadc3af9a"},"schema_version":"1.0","source":{"id":"2511.19418","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19418","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19418v3","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19418","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"7H4MTP642SB4","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"7H4MTP642SB4IUNX","created_at":"2026-08-06T01:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"7H4MTP64","created_at":"2026-08-06T01:16:45Z"}],"graph_snapshots":[{"event_id":"sha256:73249f7ff658ca687b9f367db75161396bf8728dc8a7007222eb3ce0e6abd9d5","target":"graph","created_at":"2026-08-06T01:16:45Z","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/2511.19418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that current VLMs have limited mechanisms to capture dense visual information across spatial dimensions. We introduce Chain-of-Visual-Thought (COVT), a framework that enables VLMs to reason not only in words but also through continuous visual tokens-compact latent representations that encode rich perceptual cues. Within a small budget of roughly 20 tokens, COVT ","authors_text":"Bomin wei, Jiaxin Ge, Konstantinos Kallidromitis, Stephanie Fu, Trevor Darrell, Xudong Wang, Yiming Qin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:55:19Z","title":"Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19418","kind":"arxiv","version":3},"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":"sha256:9e36862d78e45689c85b70bd236760faa5d64081665facfac7f019d66adc5c64","target":"record","created_at":"2026-08-06T01:16:45Z","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":"52a3f0f015a9efc287172c18a2b6a231b5367f635f9158337a88b45adec3b576","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T18:55:19Z","title_canon_sha256":"9b22c500b98bf270bcb429c3753e1f5863b3e58e6acf4809f841553aadc3af9a"},"schema_version":"1.0","source":{"id":"2511.19418","kind":"arxiv","version":3}},"canonical_sha256":"f9f8c9bfdcd483c451b72c220123b18c6159bcf9ac6d5c5c2d90e481de74895a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9f8c9bfdcd483c451b72c220123b18c6159bcf9ac6d5c5c2d90e481de74895a","first_computed_at":"2026-08-06T01:16:45.443571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:16:45.443571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5CVXEWR6LjkDcftnbGtrA8i72+GV4T1HVd06UITrDobZg+uOSLkdaoshxVkwmChVV9xMgUgKfoTwdelwjHEJCQ==","signature_status":"signed_v1","signed_at":"2026-08-06T01:16:45.445328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.19418","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e36862d78e45689c85b70bd236760faa5d64081665facfac7f019d66adc5c64","sha256:73249f7ff658ca687b9f367db75161396bf8728dc8a7007222eb3ce0e6abd9d5"],"state_sha256":"d30651c98955feb5ded02de0cb4f07b2d972e2615fc8863b6c97b7ded609ae03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aCYOQkCsBsggNwVk0z24srMG59kFAbYjnzNtRa91jWwEJm7vweincvXpxDP/kBsSEMuiIzeM3N0/MhK3BLNBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:11:55.836575Z","bundle_sha256":"ab99256c92d751a339b26644509c8b2b1db126e9917918dd22db9b967212c04a"}}