{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QOBGH2KYZ7Y3RU6TJALDUMLOKA","short_pith_number":"pith:QOBGH2KY","canonical_record":{"source":{"id":"2411.16824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:33:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b08ee2e721e2b2509da83e459876a3f1a26f7a0aba998a0f2a18af54e26cf9b","abstract_canon_sha256":"ec2bb5e1d3cda7e5398d1876a83ae76b7b7a48bbcf5ca72c2815236f18384283"},"schema_version":"1.0"},"canonical_sha256":"838263e958cff1b8d3d348163a316e5030992c0a125ee24bbfceb69734aa0ca1","source":{"kind":"arxiv","id":"2411.16824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16824","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16824v1","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16824","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"QOBGH2KYZ7Y3","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"QOBGH2KYZ7Y3RU6T","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"QOBGH2KY","created_at":"2026-07-05T09:40:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QOBGH2KYZ7Y3RU6TJALDUMLOKA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.16824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:33:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9b08ee2e721e2b2509da83e459876a3f1a26f7a0aba998a0f2a18af54e26cf9b","abstract_canon_sha256":"ec2bb5e1d3cda7e5398d1876a83ae76b7b7a48bbcf5ca72c2815236f18384283"},"schema_version":"1.0"},"canonical_sha256":"838263e958cff1b8d3d348163a316e5030992c0a125ee24bbfceb69734aa0ca1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:23.600416Z","signature_b64":"SkUPRLsMCZMrBcwKW/VSrdWdeyOXsj+LDD1/Rc3XjOnusf9DElhBm+xPm/qd/iwwpl8W0w0vXB6yBrPCWnbRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"838263e958cff1b8d3d348163a316e5030992c0a125ee24bbfceb69734aa0ca1","last_reissued_at":"2026-07-05T09:40:23.599949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:23.599949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.16824","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":"2026-07-05T09:40:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0U0o8IvXyroSwi6CwmIj1Y7/rH/GGyM9jlQuIroQOTB1UxjleYOw7yvImvdcO797FWAMNGmg17zsidIjLrwsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:41:31.120373Z"},"content_sha256":"4852f1a40839fb6f4d18f2d8ab6f56ab82a2ef7999c3889291492ba72fc50868","schema_version":"1.0","event_id":"sha256:4852f1a40839fb6f4d18f2d8ab6f56ab82a2ef7999c3889291492ba72fc50868"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QOBGH2KYZ7Y3RU6TJALDUMLOKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoqun Yin, Lin Li, MingAn Lin, Siwei Chen, Victor Shea-Jay Huang, Weipeng Chen, Wentao Zhang, Yaqi Zhao, Yuanyang Yin, Zenan Zhou","submitted_at":"2024-11-25T18:33:14Z","abstract_excerpt":"Does seeing always mean knowing? Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components, often using CLIP-ViT as vision backbone. However, these models frequently encounter a core issue of \"cognitive misalignment\" between the vision encoder (VE) and the large language model (LLM). Specifically, the VE's representation of visual information may not fully align with LLM's cognitive framework, leading to a mismatch where visual features exceed the language model's interpretive range. To address this, we investigate how variations in VE representations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16824","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.16824/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":"2026-07-05T09:40:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GlSGxYImTNmOV7J/NPmo5Vpj9tZYnF7ZFGFE01n8EWGnz9ObzMZJgdhYXmK5ZyjSkLWwpW5GAHmcQFTiGOdQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:41:31.120896Z"},"content_sha256":"3b290aed0f6329a9d0a251bdd530c3f7e10dbac3d359bed6b435199f2577d009","schema_version":"1.0","event_id":"sha256:3b290aed0f6329a9d0a251bdd530c3f7e10dbac3d359bed6b435199f2577d009"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA/bundle.json","state_url":"https://pith.science/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA/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":"2026-08-08T18:41:31Z","links":{"resolver":"https://pith.science/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA","bundle":"https://pith.science/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA/bundle.json","state":"https://pith.science/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOBGH2KYZ7Y3RU6TJALDUMLOKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QOBGH2KYZ7Y3RU6TJALDUMLOKA","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":"ec2bb5e1d3cda7e5398d1876a83ae76b7b7a48bbcf5ca72c2815236f18384283","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:33:14Z","title_canon_sha256":"9b08ee2e721e2b2509da83e459876a3f1a26f7a0aba998a0f2a18af54e26cf9b"},"schema_version":"1.0","source":{"id":"2411.16824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16824","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16824v1","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16824","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"QOBGH2KYZ7Y3","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"QOBGH2KYZ7Y3RU6T","created_at":"2026-07-05T09:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"QOBGH2KY","created_at":"2026-07-05T09:40:23Z"}],"graph_snapshots":[{"event_id":"sha256:3b290aed0f6329a9d0a251bdd530c3f7e10dbac3d359bed6b435199f2577d009","target":"graph","created_at":"2026-07-05T09:40:23Z","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/2411.16824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Does seeing always mean knowing? Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components, often using CLIP-ViT as vision backbone. However, these models frequently encounter a core issue of \"cognitive misalignment\" between the vision encoder (VE) and the large language model (LLM). Specifically, the VE's representation of visual information may not fully align with LLM's cognitive framework, leading to a mismatch where visual features exceed the language model's interpretive range. To address this, we investigate how variations in VE representations","authors_text":"Baoqun Yin, Lin Li, MingAn Lin, Siwei Chen, Victor Shea-Jay Huang, Weipeng Chen, Wentao Zhang, Yaqi Zhao, Yuanyang Yin, Zenan Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:33:14Z","title":"Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16824","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":"sha256:4852f1a40839fb6f4d18f2d8ab6f56ab82a2ef7999c3889291492ba72fc50868","target":"record","created_at":"2026-07-05T09:40:23Z","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":"ec2bb5e1d3cda7e5398d1876a83ae76b7b7a48bbcf5ca72c2815236f18384283","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:33:14Z","title_canon_sha256":"9b08ee2e721e2b2509da83e459876a3f1a26f7a0aba998a0f2a18af54e26cf9b"},"schema_version":"1.0","source":{"id":"2411.16824","kind":"arxiv","version":1}},"canonical_sha256":"838263e958cff1b8d3d348163a316e5030992c0a125ee24bbfceb69734aa0ca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"838263e958cff1b8d3d348163a316e5030992c0a125ee24bbfceb69734aa0ca1","first_computed_at":"2026-07-05T09:40:23.599949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:23.599949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SkUPRLsMCZMrBcwKW/VSrdWdeyOXsj+LDD1/Rc3XjOnusf9DElhBm+xPm/qd/iwwpl8W0w0vXB6yBrPCWnbRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:23.600416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4852f1a40839fb6f4d18f2d8ab6f56ab82a2ef7999c3889291492ba72fc50868","sha256:3b290aed0f6329a9d0a251bdd530c3f7e10dbac3d359bed6b435199f2577d009"],"state_sha256":"bd850cc5dabafdcc6f4aa27ffc01d61ecda64a0e293351450f1af2ff7044a13d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ex2It0FH4zHPNQf4n+ZNcoRfUZVNhhFssHR3YoD1MxMQqKGHA7o254lscOdmLeP+1ERVlsBcVvW3kMcJWj0XAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:41:31.124629Z","bundle_sha256":"64a1939ec47125efa0ef5a4e18446384f298b7201a71ef448164d07eb8e9f4fe"}}