{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IDNPU42UXN5GIM6BNLV6JJFEOD","short_pith_number":"pith:IDNPU42U","canonical_record":{"source":{"id":"2312.01597","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"e248c0fc1a62d6cae8dce2b40a3aba79ca3706a35a9257862e07b6b9d057ae1c","abstract_canon_sha256":"aede19320a35eafaa7dc7d4bbc26161e8fb7c90dd49387d80bcdec61970302b0"},"schema_version":"1.0"},"canonical_sha256":"40dafa7354bb7a6433c16aebe4a4a470cc01f2b3f96cf119af6a065e9c826297","source":{"kind":"arxiv","id":"2312.01597","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01597","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01597v4","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01597","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"IDNPU42UXN5G","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"IDNPU42UXN5GIM6B","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"IDNPU42U","created_at":"2026-07-05T09:26:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IDNPU42UXN5GIM6BNLV6JJFEOD","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01597","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"e248c0fc1a62d6cae8dce2b40a3aba79ca3706a35a9257862e07b6b9d057ae1c","abstract_canon_sha256":"aede19320a35eafaa7dc7d4bbc26161e8fb7c90dd49387d80bcdec61970302b0"},"schema_version":"1.0"},"canonical_sha256":"40dafa7354bb7a6433c16aebe4a4a470cc01f2b3f96cf119af6a065e9c826297","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:23.057595Z","signature_b64":"aTqaFfUK1aIpClDApcgLjzry7kvLHv/GHFLOyTRS6NUfG1f8IyjOVG4BJumF1hk/Cc93/QIdNJKKRgp4QYOTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40dafa7354bb7a6433c16aebe4a4a470cc01f2b3f96cf119af6a065e9c826297","last_reissued_at":"2026-07-05T09:26:23.057060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:23.057060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01597","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"55aPPVT4zk3hBdQGXHoCg8Lj/Cw71YsRaSnctzSiSoahNx5sgiUd//rZ9As0EHTM4TEV7TUioE3sx4PK1DwrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:25:17.767747Z"},"content_sha256":"9836ed5731669192f2da2b400d110f8869771aaa242511a3501dea41054d72ea","schema_version":"1.0","event_id":"sha256:9836ed5731669192f2da2b400d110f8869771aaa242511a3501dea41054d72ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IDNPU42UXN5GIM6BNLV6JJFEOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Feng Wang, Jieru Mei","submitted_at":"2023-12-04T03:18:46Z","abstract_excerpt":"Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01597","kind":"arxiv","version":4},"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/2312.01597/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":"2026-07-05T09:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p0BUGoTrrsvORynDLERb72wRgdRSYVTjWSmBTN2deZpCeQ4kLWE4QKhNW/qaX44VVjX/64ic/8h6xMQQ380GAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:25:17.768310Z"},"content_sha256":"5d7b154695522972e010488b37d508a940c57040aee093535c7cfb08c9a101e3","schema_version":"1.0","event_id":"sha256:5d7b154695522972e010488b37d508a940c57040aee093535c7cfb08c9a101e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDNPU42UXN5GIM6BNLV6JJFEOD/bundle.json","state_url":"https://pith.science/pith/IDNPU42UXN5GIM6BNLV6JJFEOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDNPU42UXN5GIM6BNLV6JJFEOD/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":"2026-08-07T00:25:17Z","links":{"resolver":"https://pith.science/pith/IDNPU42UXN5GIM6BNLV6JJFEOD","bundle":"https://pith.science/pith/IDNPU42UXN5GIM6BNLV6JJFEOD/bundle.json","state":"https://pith.science/pith/IDNPU42UXN5GIM6BNLV6JJFEOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDNPU42UXN5GIM6BNLV6JJFEOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IDNPU42UXN5GIM6BNLV6JJFEOD","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":"aede19320a35eafaa7dc7d4bbc26161e8fb7c90dd49387d80bcdec61970302b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:46Z","title_canon_sha256":"e248c0fc1a62d6cae8dce2b40a3aba79ca3706a35a9257862e07b6b9d057ae1c"},"schema_version":"1.0","source":{"id":"2312.01597","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01597","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01597v4","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01597","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"IDNPU42UXN5G","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"IDNPU42UXN5GIM6B","created_at":"2026-07-05T09:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"IDNPU42U","created_at":"2026-07-05T09:26:23Z"}],"graph_snapshots":[{"event_id":"sha256:5d7b154695522972e010488b37d508a940c57040aee093535c7cfb08c9a101e3","target":"graph","created_at":"2026-07-05T09:26:23Z","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/2312.01597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention,","authors_text":"Alan Yuille, Feng Wang, Jieru Mei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:46Z","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01597","kind":"arxiv","version":4},"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":"sha256:9836ed5731669192f2da2b400d110f8869771aaa242511a3501dea41054d72ea","target":"record","created_at":"2026-07-05T09:26:23Z","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":"aede19320a35eafaa7dc7d4bbc26161e8fb7c90dd49387d80bcdec61970302b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:46Z","title_canon_sha256":"e248c0fc1a62d6cae8dce2b40a3aba79ca3706a35a9257862e07b6b9d057ae1c"},"schema_version":"1.0","source":{"id":"2312.01597","kind":"arxiv","version":4}},"canonical_sha256":"40dafa7354bb7a6433c16aebe4a4a470cc01f2b3f96cf119af6a065e9c826297","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40dafa7354bb7a6433c16aebe4a4a470cc01f2b3f96cf119af6a065e9c826297","first_computed_at":"2026-07-05T09:26:23.057060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:23.057060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aTqaFfUK1aIpClDApcgLjzry7kvLHv/GHFLOyTRS6NUfG1f8IyjOVG4BJumF1hk/Cc93/QIdNJKKRgp4QYOTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:23.057595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01597","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9836ed5731669192f2da2b400d110f8869771aaa242511a3501dea41054d72ea","sha256:5d7b154695522972e010488b37d508a940c57040aee093535c7cfb08c9a101e3"],"state_sha256":"471566e5967d63c4e080503a40e739b0fb101c33469a55654ccf40c75a925166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGgpsHJ1yoo2hJlFW+dqn5hqJItdzjG6DTGpMFJmes3Wp2D2KVZSjtMpk/cqDwdBOyg26IrkyW91aNYh6YqxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:25:17.773124Z","bundle_sha256":"97d337471a517f499501ab5fbd0f22e990418a0b8a30e260a052abf99729d96a"}}