{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NPTNAW3D7CVCKU5N7DIJZ6MT6K","short_pith_number":"pith:NPTNAW3D","canonical_record":{"source":{"id":"2406.14544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T17:54:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9ba6ce720a40f6dae67c211f8838e3c6b9a303ae28005c6b558aee911232c770","abstract_canon_sha256":"1d66cd0ca72114fe2a2a8d6e7f090969ada6e80bb0c759f0fb6f31854b37e381"},"schema_version":"1.0"},"canonical_sha256":"6be6d05b63f8aa2553adf8d09cf993f2a05b0c4479f2a64fc0f55f24dbc2330b","source":{"kind":"arxiv","id":"2406.14544","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14544","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14544v1","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14544","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"pith_short_12","alias_value":"NPTNAW3D7CVC","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"pith_short_16","alias_value":"NPTNAW3D7CVCKU5N","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"pith_short_8","alias_value":"NPTNAW3D","created_at":"2026-07-05T08:34:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NPTNAW3D7CVCKU5N7DIJZ6MT6K","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T17:54:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9ba6ce720a40f6dae67c211f8838e3c6b9a303ae28005c6b558aee911232c770","abstract_canon_sha256":"1d66cd0ca72114fe2a2a8d6e7f090969ada6e80bb0c759f0fb6f31854b37e381"},"schema_version":"1.0"},"canonical_sha256":"6be6d05b63f8aa2553adf8d09cf993f2a05b0c4479f2a64fc0f55f24dbc2330b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:52.053464Z","signature_b64":"ngdQ0cGqIK99II8RGz36OZ6kvFpfIBcjLsY/8ZLs1C5Wyi7hpI4huEusp//zJjlz7f8LCKErvvTFnOsFmvWEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be6d05b63f8aa2553adf8d09cf993f2a05b0c4479f2a64fc0f55f24dbc2330b","last_reissued_at":"2026-07-05T08:34:52.053007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:52.053007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14544","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":"2026-07-05T08:34:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mZs2VMX0kr9FtV7gRMUP1Qjbb6GsVd1w9jLz5KamIpKtl9ilhhQ0NyXhVmFSa69xA7j0VlYJcgZWSLjGBe9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:49:08.125830Z"},"content_sha256":"36a80067a28b69750e55a76ed49256655cc75a59c01ace72a9a6fc36a201cd76","schema_version":"1.0","event_id":"sha256:36a80067a28b69750e55a76ed49256655cc75a59c01ace72a9a6fc36a201cd76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NPTNAW3D7CVCKU5N7DIJZ6MT6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Junming Yang, Kai Chen, Lin Chen, Songyang Zhang, Xinyu Fang, Yuxuan Qiao","submitted_at":"2024-06-20T17:54:03Z","abstract_excerpt":"Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is crucial for model refinement, despite the inherent difficulty due to the intertwined nature of seeing and reasoning in existing VLMs. To tackle this issue, we present Prism, an innovative framework designed to disentangle the perception and reasoning processes involved in visual question solving. Prism comprises two distinct stages: a perception stage that utilizes a VLM to ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14544","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/2406.14544/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":"2026-07-05T08:34:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBZqR4YA879HrXzzj0r9p1K9IyhmTZrR3P8e6t0I9M2eoTAIjFj1f4S8O//hmdcgocQV+64zlYnAmLCtqXShCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:49:08.126802Z"},"content_sha256":"b53eddf6ebc4091de4fc0ab6a7bf84ea491c59981b2147f5bc7bf0f9e59ef964","schema_version":"1.0","event_id":"sha256:b53eddf6ebc4091de4fc0ab6a7bf84ea491c59981b2147f5bc7bf0f9e59ef964"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K/bundle.json","state_url":"https://pith.science/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K/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":"2026-08-12T08:49:08Z","links":{"resolver":"https://pith.science/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K","bundle":"https://pith.science/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K/bundle.json","state":"https://pith.science/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NPTNAW3D7CVCKU5N7DIJZ6MT6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NPTNAW3D7CVCKU5N7DIJZ6MT6K","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":"1d66cd0ca72114fe2a2a8d6e7f090969ada6e80bb0c759f0fb6f31854b37e381","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T17:54:03Z","title_canon_sha256":"9ba6ce720a40f6dae67c211f8838e3c6b9a303ae28005c6b558aee911232c770"},"schema_version":"1.0","source":{"id":"2406.14544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14544","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14544v1","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14544","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"pith_short_12","alias_value":"NPTNAW3D7CVC","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"pith_short_16","alias_value":"NPTNAW3D7CVCKU5N","created_at":"2026-07-05T08:34:52Z"},{"alias_kind":"pith_short_8","alias_value":"NPTNAW3D","created_at":"2026-07-05T08:34:52Z"}],"graph_snapshots":[{"event_id":"sha256:b53eddf6ebc4091de4fc0ab6a7bf84ea491c59981b2147f5bc7bf0f9e59ef964","target":"graph","created_at":"2026-07-05T08:34:52Z","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/2406.14544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is crucial for model refinement, despite the inherent difficulty due to the intertwined nature of seeing and reasoning in existing VLMs. To tackle this issue, we present Prism, an innovative framework designed to disentangle the perception and reasoning processes involved in visual question solving. Prism comprises two distinct stages: a perception stage that utilizes a VLM to ex","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Junming Yang, Kai Chen, Lin Chen, Songyang Zhang, Xinyu Fang, Yuxuan Qiao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T17:54:03Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14544","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":"sha256:36a80067a28b69750e55a76ed49256655cc75a59c01ace72a9a6fc36a201cd76","target":"record","created_at":"2026-07-05T08:34:52Z","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":"1d66cd0ca72114fe2a2a8d6e7f090969ada6e80bb0c759f0fb6f31854b37e381","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T17:54:03Z","title_canon_sha256":"9ba6ce720a40f6dae67c211f8838e3c6b9a303ae28005c6b558aee911232c770"},"schema_version":"1.0","source":{"id":"2406.14544","kind":"arxiv","version":1}},"canonical_sha256":"6be6d05b63f8aa2553adf8d09cf993f2a05b0c4479f2a64fc0f55f24dbc2330b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6be6d05b63f8aa2553adf8d09cf993f2a05b0c4479f2a64fc0f55f24dbc2330b","first_computed_at":"2026-07-05T08:34:52.053007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:52.053007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ngdQ0cGqIK99II8RGz36OZ6kvFpfIBcjLsY/8ZLs1C5Wyi7hpI4huEusp//zJjlz7f8LCKErvvTFnOsFmvWEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:52.053464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36a80067a28b69750e55a76ed49256655cc75a59c01ace72a9a6fc36a201cd76","sha256:b53eddf6ebc4091de4fc0ab6a7bf84ea491c59981b2147f5bc7bf0f9e59ef964"],"state_sha256":"fe4cf20651df1f495e2fe878ce5a887f3e31d315dcf036c07067b5e8ca93650b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3gVpPusiHBVZ7wxWKuY7A6UzIyjMuYiGQUF2yftDI2ACLnRMU5UY1/HHLTtlPG5MHSsKSrDDX2EQ3JZ5VGPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:49:08.194919Z","bundle_sha256":"6673fbd633a3c2422b8605f4e841f5a213f3416faae99e111de0da2dfe538858"}}