{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KA4RD346R3HMMFPX3IXPN22NYI","short_pith_number":"pith:KA4RD346","canonical_record":{"source":{"id":"2312.08548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T22:20:45Z","cross_cats_sorted":[],"title_canon_sha256":"5fa75716e69277258968780e7e3b24022c0cf23b5eab596d7d2d4457cda432c5","abstract_canon_sha256":"20e2dc073cd907e70bbcfff9827f785cc1558606b2f4dcefcbc7e046728e613f"},"schema_version":"1.0"},"canonical_sha256":"503911ef9e8ecec615f7da2ef6eb4dc201365b89b8b5fe03d02c50591c233926","source":{"kind":"arxiv","id":"2312.08548","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08548","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08548v1","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08548","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"KA4RD346R3HM","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"KA4RD346R3HMMFPX","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"KA4RD346","created_at":"2026-07-05T07:24:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KA4RD346R3HMMFPX3IXPN22NYI","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T22:20:45Z","cross_cats_sorted":[],"title_canon_sha256":"5fa75716e69277258968780e7e3b24022c0cf23b5eab596d7d2d4457cda432c5","abstract_canon_sha256":"20e2dc073cd907e70bbcfff9827f785cc1558606b2f4dcefcbc7e046728e613f"},"schema_version":"1.0"},"canonical_sha256":"503911ef9e8ecec615f7da2ef6eb4dc201365b89b8b5fe03d02c50591c233926","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:05.850674Z","signature_b64":"ppbHyJ+DT4pv8Nuzlw6nEIto+V+SHsuV31FlVI7qHw1H0QV/S0tKdHSzXomhFbyPwiM50rBUD6tq5YTFHprkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"503911ef9e8ecec615f7da2ef6eb4dc201365b89b8b5fe03d02c50591c233926","last_reissued_at":"2026-07-05T07:24:05.850213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:05.850213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08548","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":"2026-07-05T07:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EiIk7fi630+tKQxH+wi9/m6bBbDMQtJV0u5U5Wl+1JVogtqSbexAoiPrfPllDjYcU+db/xrJLh8nO8PqeR0SAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:50.177735Z"},"content_sha256":"780a68582ac75c815af316949b4cd4c1ffa60f1382fe2bf1dde4e2ee0ed2e33d","schema_version":"1.0","event_id":"sha256:780a68582ac75c815af316949b4cd4c1ffa60f1382fe2bf1dde4e2ee0ed2e33d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KA4RD346R3HMMFPX3IXPN22NYI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthias M\\\"uller, Mykola Lavreniuk, Peter Wonka, Shariq Farooq Bhat","submitted_at":"2023-12-13T22:20:45Z","abstract_excerpt":"This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First, we develop the Inverse Multi-Attentive Feature Refinement (IMAFR) module which enhances feature learning capabilities by aggregating spatial information from higher pyramid levels. Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone. The resulting architecture is suitable for a wide variety o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08548","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/2312.08548/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":"2026-07-05T07:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7pGmkFX1gnPKzWVslLboOxK7FAidqrscXw3gVQ3sCgc56irWJZOqBYgwVto4aTzoa5T0bFCC6tDRz6c+LZO5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:50.178694Z"},"content_sha256":"8b7f3bef2ee49fde78392b6e9815172a1519539b9e90e97c3c9d90022abbba53","schema_version":"1.0","event_id":"sha256:8b7f3bef2ee49fde78392b6e9815172a1519539b9e90e97c3c9d90022abbba53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KA4RD346R3HMMFPX3IXPN22NYI/bundle.json","state_url":"https://pith.science/pith/KA4RD346R3HMMFPX3IXPN22NYI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KA4RD346R3HMMFPX3IXPN22NYI/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":"2026-08-08T16:57:50Z","links":{"resolver":"https://pith.science/pith/KA4RD346R3HMMFPX3IXPN22NYI","bundle":"https://pith.science/pith/KA4RD346R3HMMFPX3IXPN22NYI/bundle.json","state":"https://pith.science/pith/KA4RD346R3HMMFPX3IXPN22NYI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KA4RD346R3HMMFPX3IXPN22NYI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KA4RD346R3HMMFPX3IXPN22NYI","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":"20e2dc073cd907e70bbcfff9827f785cc1558606b2f4dcefcbc7e046728e613f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T22:20:45Z","title_canon_sha256":"5fa75716e69277258968780e7e3b24022c0cf23b5eab596d7d2d4457cda432c5"},"schema_version":"1.0","source":{"id":"2312.08548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08548","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08548v1","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08548","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"KA4RD346R3HM","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"KA4RD346R3HMMFPX","created_at":"2026-07-05T07:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"KA4RD346","created_at":"2026-07-05T07:24:05Z"}],"graph_snapshots":[{"event_id":"sha256:8b7f3bef2ee49fde78392b6e9815172a1519539b9e90e97c3c9d90022abbba53","target":"graph","created_at":"2026-07-05T07:24:05Z","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/2312.08548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First, we develop the Inverse Multi-Attentive Feature Refinement (IMAFR) module which enhances feature learning capabilities by aggregating spatial information from higher pyramid levels. Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone. The resulting architecture is suitable for a wide variety o","authors_text":"Matthias M\\\"uller, Mykola Lavreniuk, Peter Wonka, Shariq Farooq Bhat","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T22:20:45Z","title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08548","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":"sha256:780a68582ac75c815af316949b4cd4c1ffa60f1382fe2bf1dde4e2ee0ed2e33d","target":"record","created_at":"2026-07-05T07:24:05Z","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":"20e2dc073cd907e70bbcfff9827f785cc1558606b2f4dcefcbc7e046728e613f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T22:20:45Z","title_canon_sha256":"5fa75716e69277258968780e7e3b24022c0cf23b5eab596d7d2d4457cda432c5"},"schema_version":"1.0","source":{"id":"2312.08548","kind":"arxiv","version":1}},"canonical_sha256":"503911ef9e8ecec615f7da2ef6eb4dc201365b89b8b5fe03d02c50591c233926","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"503911ef9e8ecec615f7da2ef6eb4dc201365b89b8b5fe03d02c50591c233926","first_computed_at":"2026-07-05T07:24:05.850213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:05.850213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ppbHyJ+DT4pv8Nuzlw6nEIto+V+SHsuV31FlVI7qHw1H0QV/S0tKdHSzXomhFbyPwiM50rBUD6tq5YTFHprkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:05.850674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:780a68582ac75c815af316949b4cd4c1ffa60f1382fe2bf1dde4e2ee0ed2e33d","sha256:8b7f3bef2ee49fde78392b6e9815172a1519539b9e90e97c3c9d90022abbba53"],"state_sha256":"725f987fe9b55507c169aa153730053676cef29d6af5ff72c7b100d2f8c01797"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKazLFWJvb/vfWNN/HXs0QN4PgwmP6DBW8a5KUoKwYEvI8oRcP3K5Tekr/cqptTytMEfx0vMi2xB9tDzuC2cDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:57:50.185999Z","bundle_sha256":"afee76f51fb71dbc023314e2ff310f7afbd9d852231b28e28472e3803869d24a"}}