{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SJOT27JVPIO4KSPN5ZGPCO7WX6","short_pith_number":"pith:SJOT27JV","canonical_record":{"source":{"id":"2206.05281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-10T07:03:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7cab845b9dc03937601fd4a56af2b636ff305391b7f290e54a108a2b1c456a1d","abstract_canon_sha256":"1245f18cb2885d7ca67389574ffde1cf44f80bace76729d0c2b230ddf5fdf6c6"},"schema_version":"1.0"},"canonical_sha256":"925d3d7d357a1dc549edee4cf13bf6bf8ecf73b2757d57b5de2ee840419dfdb2","source":{"kind":"arxiv","id":"2206.05281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05281","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05281v1","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05281","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"SJOT27JVPIO4","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"SJOT27JVPIO4KSPN","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"SJOT27JV","created_at":"2026-07-05T04:30:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SJOT27JVPIO4KSPN5ZGPCO7WX6","target":"record","payload":{"canonical_record":{"source":{"id":"2206.05281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-10T07:03:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7cab845b9dc03937601fd4a56af2b636ff305391b7f290e54a108a2b1c456a1d","abstract_canon_sha256":"1245f18cb2885d7ca67389574ffde1cf44f80bace76729d0c2b230ddf5fdf6c6"},"schema_version":"1.0"},"canonical_sha256":"925d3d7d357a1dc549edee4cf13bf6bf8ecf73b2757d57b5de2ee840419dfdb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:57.848966Z","signature_b64":"xMQk93EoOo6Niz/jgxEpP1SUoYZTQNrhrsLF7eszqWpo++55IvJhCKOqXtBu3Wis2IalO/W52dRZZnI4LsrYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925d3d7d357a1dc549edee4cf13bf6bf8ecf73b2757d57b5de2ee840419dfdb2","last_reissued_at":"2026-07-05T04:30:57.848583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:57.848583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.05281","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":"2026-07-05T04:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwxMxVeARSNCsIvqi/98xyZVQljGWwu2gnjxvVk9/kO99Q03XyihXec+WNeAsieLP2OdiAf6r+XaWWc8ywbPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:10:27.965489Z"},"content_sha256":"83e698fdb29f380bb45be8f5f81aebfc1ac4e35a98fc63c46415c2c187430d0c","schema_version":"1.0","event_id":"sha256:83e698fdb29f380bb45be8f5f81aebfc1ac4e35a98fc63c46415c2c187430d0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SJOT27JVPIO4KSPN5ZGPCO7WX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fabian Deuser, Konrad Habel, Norbert Oswald, Philipp J. R\\\"osch","submitted_at":"2022-06-10T07:03:52Z","abstract_excerpt":"Current architectures for multi-modality tasks such as visual question answering suffer from their high complexity. As a result, these architectures are difficult to train and require high computational resources. To address these problems we present a CLIP-based architecture that does not require any fine-tuning of the feature extractors. A simple linear classifier is used on the concatenated features of the image and text encoder. During training an auxiliary loss is added which operates on the answer types. The resulting classification is then used as an attention gate on the answer class s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05281","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/2206.05281/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":"2026-07-05T04:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nqVOISi4J7MfUlkqe296A+Gsad4NhrTjBh4D9FV6SDlUWUC1UZtBh2li62DIQM74pZGGzKUhw9zrjuBXeLOnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:10:27.965873Z"},"content_sha256":"b73250a87f2041e80d1bcbac728b9ff4b0805024b06ac5cf84caa8998b0d127b","schema_version":"1.0","event_id":"sha256:b73250a87f2041e80d1bcbac728b9ff4b0805024b06ac5cf84caa8998b0d127b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6/bundle.json","state_url":"https://pith.science/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6/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":"2026-07-07T07:10:27Z","links":{"resolver":"https://pith.science/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6","bundle":"https://pith.science/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6/bundle.json","state":"https://pith.science/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJOT27JVPIO4KSPN5ZGPCO7WX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SJOT27JVPIO4KSPN5ZGPCO7WX6","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":"1245f18cb2885d7ca67389574ffde1cf44f80bace76729d0c2b230ddf5fdf6c6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-10T07:03:52Z","title_canon_sha256":"7cab845b9dc03937601fd4a56af2b636ff305391b7f290e54a108a2b1c456a1d"},"schema_version":"1.0","source":{"id":"2206.05281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05281","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05281v1","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05281","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"SJOT27JVPIO4","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"SJOT27JVPIO4KSPN","created_at":"2026-07-05T04:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"SJOT27JV","created_at":"2026-07-05T04:30:57Z"}],"graph_snapshots":[{"event_id":"sha256:b73250a87f2041e80d1bcbac728b9ff4b0805024b06ac5cf84caa8998b0d127b","target":"graph","created_at":"2026-07-05T04:30:57Z","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/2206.05281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current architectures for multi-modality tasks such as visual question answering suffer from their high complexity. As a result, these architectures are difficult to train and require high computational resources. To address these problems we present a CLIP-based architecture that does not require any fine-tuning of the feature extractors. A simple linear classifier is used on the concatenated features of the image and text encoder. During training an auxiliary loss is added which operates on the answer types. The resulting classification is then used as an attention gate on the answer class s","authors_text":"Fabian Deuser, Konrad Habel, Norbert Oswald, Philipp J. R\\\"osch","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-10T07:03:52Z","title":"Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05281","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":"sha256:83e698fdb29f380bb45be8f5f81aebfc1ac4e35a98fc63c46415c2c187430d0c","target":"record","created_at":"2026-07-05T04:30:57Z","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":"1245f18cb2885d7ca67389574ffde1cf44f80bace76729d0c2b230ddf5fdf6c6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-10T07:03:52Z","title_canon_sha256":"7cab845b9dc03937601fd4a56af2b636ff305391b7f290e54a108a2b1c456a1d"},"schema_version":"1.0","source":{"id":"2206.05281","kind":"arxiv","version":1}},"canonical_sha256":"925d3d7d357a1dc549edee4cf13bf6bf8ecf73b2757d57b5de2ee840419dfdb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"925d3d7d357a1dc549edee4cf13bf6bf8ecf73b2757d57b5de2ee840419dfdb2","first_computed_at":"2026-07-05T04:30:57.848583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:57.848583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xMQk93EoOo6Niz/jgxEpP1SUoYZTQNrhrsLF7eszqWpo++55IvJhCKOqXtBu3Wis2IalO/W52dRZZnI4LsrYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:57.848966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.05281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83e698fdb29f380bb45be8f5f81aebfc1ac4e35a98fc63c46415c2c187430d0c","sha256:b73250a87f2041e80d1bcbac728b9ff4b0805024b06ac5cf84caa8998b0d127b"],"state_sha256":"13ca94ab8d1a5009b3a82f9fe226b87032ad878a5228b0b86e8494cf7bea1b62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6v7E/L//Lhlh0Jh8Cf6Z0UFLnemEa06Vzw+f7yKAvwY5JFEKCAefU8/C3dO5m2O5yzN7G2M6neqz7d00h2QAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:10:27.967792Z","bundle_sha256":"bd149114eaadb302ed7808f47403d899f411a7a7d4d67021fee33c044cec4f35"}}