{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EFZKUKOIJNVAUPHG73I6KSU2KI","short_pith_number":"pith:EFZKUKOI","canonical_record":{"source":{"id":"2509.09311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T09:54:25Z","cross_cats_sorted":[],"title_canon_sha256":"92040215a47ab7af9edac73e7a6966528ee92faa2e2804c39e6940a363283530","abstract_canon_sha256":"d40dd9c3ad200a1787cdf4c7a9766160985ed582d997effb3b72e7e8b8403c8f"},"schema_version":"1.0"},"canonical_sha256":"2172aa29c84b6a0a3ce6fed1e54a9a52152ef38a9afeb1acdf85b0a145ebd436","source":{"kind":"arxiv","id":"2509.09311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09311","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09311v1","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09311","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"EFZKUKOIJNVA","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"EFZKUKOIJNVAUPHG","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"EFZKUKOI","created_at":"2026-07-05T12:09:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EFZKUKOIJNVAUPHG73I6KSU2KI","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T09:54:25Z","cross_cats_sorted":[],"title_canon_sha256":"92040215a47ab7af9edac73e7a6966528ee92faa2e2804c39e6940a363283530","abstract_canon_sha256":"d40dd9c3ad200a1787cdf4c7a9766160985ed582d997effb3b72e7e8b8403c8f"},"schema_version":"1.0"},"canonical_sha256":"2172aa29c84b6a0a3ce6fed1e54a9a52152ef38a9afeb1acdf85b0a145ebd436","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:33.781462Z","signature_b64":"p1RO+RtsBVipPfMZltO0kM4NJn8iBcuy6l/8jt99xn2CzQU4kqMTJouBas9OD7nwF44S2l4Et0PHLMcTRoljBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2172aa29c84b6a0a3ce6fed1e54a9a52152ef38a9afeb1acdf85b0a145ebd436","last_reissued_at":"2026-07-05T12:09:33.780951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:33.780951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09311","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":"2026-07-05T12:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fki/12j8mciVQCEVDaA6WPd/OVNY/zgx2ScuQgKcF2BaCaSO4KGqgBXmtKpwzkECy8bkHLaCy3bht6Sqm/h8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:09:48.061567Z"},"content_sha256":"5c74a95fb475f6fcfc08558fb51cc9100f51c7b160f988b30f65af65206ad9c4","schema_version":"1.0","event_id":"sha256:5c74a95fb475f6fcfc08558fb51cc9100f51c7b160f988b30f65af65206ad9c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EFZKUKOIJNVAUPHG73I6KSU2KI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Recognition with Vision and Language Embeddings of VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Illia Volkov, Jiri Matas, Klara Janouskova, Nikita Kisel","submitted_at":"2025-09-11T09:54:25Z","abstract_excerpt":"Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both language-guided and vision-only image classification with a diverse set of dual-encoder VLMs, including both well-established and recent models such as SigLIP 2 and RADIOv2.5. The performance is compared in a standard setup on the ImageNet-1k validation set and its label-corrected variant. The key factors affecting accuracy are analysed, including prompt design,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09311","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/2509.09311/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":"2026-07-05T12:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1KD/ZXMVeJV4UftkZshKqtumAXDK+FwfsCRMeorSGeLal5DEaE3PCs4fAJQ8V2ylQZt87O2E/+pzfH/mKmtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:09:48.062083Z"},"content_sha256":"3056b3436065d1f6c7f7e0170f5caa3536dfc0b6ad9a3142b506263d79215744","schema_version":"1.0","event_id":"sha256:3056b3436065d1f6c7f7e0170f5caa3536dfc0b6ad9a3142b506263d79215744"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFZKUKOIJNVAUPHG73I6KSU2KI/bundle.json","state_url":"https://pith.science/pith/EFZKUKOIJNVAUPHG73I6KSU2KI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFZKUKOIJNVAUPHG73I6KSU2KI/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":"2026-08-23T01:09:48Z","links":{"resolver":"https://pith.science/pith/EFZKUKOIJNVAUPHG73I6KSU2KI","bundle":"https://pith.science/pith/EFZKUKOIJNVAUPHG73I6KSU2KI/bundle.json","state":"https://pith.science/pith/EFZKUKOIJNVAUPHG73I6KSU2KI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFZKUKOIJNVAUPHG73I6KSU2KI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EFZKUKOIJNVAUPHG73I6KSU2KI","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":"d40dd9c3ad200a1787cdf4c7a9766160985ed582d997effb3b72e7e8b8403c8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T09:54:25Z","title_canon_sha256":"92040215a47ab7af9edac73e7a6966528ee92faa2e2804c39e6940a363283530"},"schema_version":"1.0","source":{"id":"2509.09311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09311","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09311v1","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09311","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"EFZKUKOIJNVA","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"EFZKUKOIJNVAUPHG","created_at":"2026-07-05T12:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"EFZKUKOI","created_at":"2026-07-05T12:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:3056b3436065d1f6c7f7e0170f5caa3536dfc0b6ad9a3142b506263d79215744","target":"graph","created_at":"2026-07-05T12:09:33Z","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/2509.09311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both language-guided and vision-only image classification with a diverse set of dual-encoder VLMs, including both well-established and recent models such as SigLIP 2 and RADIOv2.5. The performance is compared in a standard setup on the ImageNet-1k validation set and its label-corrected variant. The key factors affecting accuracy are analysed, including prompt design,","authors_text":"Illia Volkov, Jiri Matas, Klara Janouskova, Nikita Kisel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T09:54:25Z","title":"Image Recognition with Vision and Language Embeddings of VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09311","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":"sha256:5c74a95fb475f6fcfc08558fb51cc9100f51c7b160f988b30f65af65206ad9c4","target":"record","created_at":"2026-07-05T12:09:33Z","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":"d40dd9c3ad200a1787cdf4c7a9766160985ed582d997effb3b72e7e8b8403c8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T09:54:25Z","title_canon_sha256":"92040215a47ab7af9edac73e7a6966528ee92faa2e2804c39e6940a363283530"},"schema_version":"1.0","source":{"id":"2509.09311","kind":"arxiv","version":1}},"canonical_sha256":"2172aa29c84b6a0a3ce6fed1e54a9a52152ef38a9afeb1acdf85b0a145ebd436","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2172aa29c84b6a0a3ce6fed1e54a9a52152ef38a9afeb1acdf85b0a145ebd436","first_computed_at":"2026-07-05T12:09:33.780951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:33.780951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p1RO+RtsBVipPfMZltO0kM4NJn8iBcuy6l/8jt99xn2CzQU4kqMTJouBas9OD7nwF44S2l4Et0PHLMcTRoljBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:33.781462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c74a95fb475f6fcfc08558fb51cc9100f51c7b160f988b30f65af65206ad9c4","sha256:3056b3436065d1f6c7f7e0170f5caa3536dfc0b6ad9a3142b506263d79215744"],"state_sha256":"f97fa03a5bf1bd190170ed4588b5c6fd0eae85128f48e486a1b727a9cea9605d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzaxazDPyJjrqnoZwukKmNpuCCZq/QkPeUG2luwFHxjkV2UuypZmApuf4axgdTr4OWJlEhTohW2nuXd8ee8WBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T01:09:48.066006Z","bundle_sha256":"c5e69d360e9f8bf03e97410378b70137633a43abb5e4d9e8bebf7a0da5d93430"}}