{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2TSQYNWWJAIKNYWFBWYWAENH2U","short_pith_number":"pith:2TSQYNWW","canonical_record":{"source":{"id":"2504.16801","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T15:20:53Z","cross_cats_sorted":[],"title_canon_sha256":"0b9d0fe8065436df6f5c52fcdbe56c86d88697e2133c2b7954e1cd2e153415e4","abstract_canon_sha256":"5da5841c72b48c2edc0886b0a22d42cc1f6bec146c0b8d2c9727f11258624f66"},"schema_version":"1.0"},"canonical_sha256":"d4e50c36d64810a6e2c50db16011a7d528ccdd89c7c0bf90bd64e920a9b8934c","source":{"kind":"arxiv","id":"2504.16801","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16801","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16801v3","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16801","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"2TSQYNWWJAIK","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"2TSQYNWWJAIKNYWF","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"2TSQYNWW","created_at":"2026-07-05T11:59:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2TSQYNWWJAIKNYWFBWYWAENH2U","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16801","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T15:20:53Z","cross_cats_sorted":[],"title_canon_sha256":"0b9d0fe8065436df6f5c52fcdbe56c86d88697e2133c2b7954e1cd2e153415e4","abstract_canon_sha256":"5da5841c72b48c2edc0886b0a22d42cc1f6bec146c0b8d2c9727f11258624f66"},"schema_version":"1.0"},"canonical_sha256":"d4e50c36d64810a6e2c50db16011a7d528ccdd89c7c0bf90bd64e920a9b8934c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:13.367645Z","signature_b64":"pJPA4Ga7hLIc1uBuG4VJ80lPZ1jwCLqFSR3cP5rUUeCukzXae5rCE4YgU8ltCb9ttMYcqpUu0Asebz/LXvPPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4e50c36d64810a6e2c50db16011a7d528ccdd89c7c0bf90bd64e920a9b8934c","last_reissued_at":"2026-07-05T11:59:13.367117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:13.367117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16801","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:59:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MapnRkyse+btKZJl8+vHdl86S38ISvc8RTxDBiq4a8tZTbYgtTJTyJ48JqpIxL1u+66InfPO8a//qBbQfIDqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:39:29.551197Z"},"content_sha256":"4076203cbf9b373823b6941b02eedff1c44bffaebb18043579af2308ecf16e43","schema_version":"1.0","event_id":"sha256:4076203cbf9b373823b6941b02eedff1c44bffaebb18043579af2308ecf16e43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2TSQYNWWJAIKNYWFBWYWAENH2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Xu, Jun Wang, Kaicheng Yang, Xiaoxing Hu, Yupei Wang, Ziyong Feng","submitted_at":"2025-04-23T15:20:53Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional concepts, such as relations and attributes. Although recent studies employ global hard negative samples to improve compositional understanding, these methods significantly compromise the model's inherent general capabilities by forcibly distancing textual negative samples from images in the embedding space. To overcome this limitation, we introduce a Decoupled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16801","kind":"arxiv","version":3},"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/2504.16801/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":"2026-07-05T11:59:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhQIJjNu4Mn3Q4TrHA/RXRd3fvPueSZCD1aGsDzFlTAtlZiR8As8Yjp9RXXBEB4TWo+C1iUBJo868bcfuJ65Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:39:29.552171Z"},"content_sha256":"928efabd1ea7ef481959120fe4deda8e8a62d13cf24682e303603d56cb394b16","schema_version":"1.0","event_id":"sha256:928efabd1ea7ef481959120fe4deda8e8a62d13cf24682e303603d56cb394b16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TSQYNWWJAIKNYWFBWYWAENH2U/bundle.json","state_url":"https://pith.science/pith/2TSQYNWWJAIKNYWFBWYWAENH2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TSQYNWWJAIKNYWFBWYWAENH2U/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":"2026-08-03T18:39:29Z","links":{"resolver":"https://pith.science/pith/2TSQYNWWJAIKNYWFBWYWAENH2U","bundle":"https://pith.science/pith/2TSQYNWWJAIKNYWFBWYWAENH2U/bundle.json","state":"https://pith.science/pith/2TSQYNWWJAIKNYWFBWYWAENH2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TSQYNWWJAIKNYWFBWYWAENH2U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2TSQYNWWJAIKNYWFBWYWAENH2U","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":"5da5841c72b48c2edc0886b0a22d42cc1f6bec146c0b8d2c9727f11258624f66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T15:20:53Z","title_canon_sha256":"0b9d0fe8065436df6f5c52fcdbe56c86d88697e2133c2b7954e1cd2e153415e4"},"schema_version":"1.0","source":{"id":"2504.16801","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16801","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16801v3","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16801","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"2TSQYNWWJAIK","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"2TSQYNWWJAIKNYWF","created_at":"2026-07-05T11:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"2TSQYNWW","created_at":"2026-07-05T11:59:13Z"}],"graph_snapshots":[{"event_id":"sha256:928efabd1ea7ef481959120fe4deda8e8a62d13cf24682e303603d56cb394b16","target":"graph","created_at":"2026-07-05T11:59:13Z","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/2504.16801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional concepts, such as relations and attributes. Although recent studies employ global hard negative samples to improve compositional understanding, these methods significantly compromise the model's inherent general capabilities by forcibly distancing textual negative samples from images in the embedding space. To overcome this limitation, we introduce a Decoupled ","authors_text":"Haoran Xu, Jun Wang, Kaicheng Yang, Xiaoxing Hu, Yupei Wang, Ziyong Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T15:20:53Z","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16801","kind":"arxiv","version":3},"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":"sha256:4076203cbf9b373823b6941b02eedff1c44bffaebb18043579af2308ecf16e43","target":"record","created_at":"2026-07-05T11:59:13Z","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":"5da5841c72b48c2edc0886b0a22d42cc1f6bec146c0b8d2c9727f11258624f66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T15:20:53Z","title_canon_sha256":"0b9d0fe8065436df6f5c52fcdbe56c86d88697e2133c2b7954e1cd2e153415e4"},"schema_version":"1.0","source":{"id":"2504.16801","kind":"arxiv","version":3}},"canonical_sha256":"d4e50c36d64810a6e2c50db16011a7d528ccdd89c7c0bf90bd64e920a9b8934c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4e50c36d64810a6e2c50db16011a7d528ccdd89c7c0bf90bd64e920a9b8934c","first_computed_at":"2026-07-05T11:59:13.367117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:13.367117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pJPA4Ga7hLIc1uBuG4VJ80lPZ1jwCLqFSR3cP5rUUeCukzXae5rCE4YgU8ltCb9ttMYcqpUu0Asebz/LXvPPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:13.367645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16801","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4076203cbf9b373823b6941b02eedff1c44bffaebb18043579af2308ecf16e43","sha256:928efabd1ea7ef481959120fe4deda8e8a62d13cf24682e303603d56cb394b16"],"state_sha256":"0ca05e36fb458bbdb7fde672e938ddc03e5226f3c5275990540a08b3ed16e6a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+r/iKhtp7SpAbXm0FZ9H5z/7gnwrGHXiFKRpGSCkmsxlhJx8lGpUdeZRG32o7BFLHenPMYOQ4mfDD0bCe6XQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:39:29.579676Z","bundle_sha256":"e05e94671a5e0cf20e1d518e1282f6b728d829bb46df3d82b0ba3f798fc729db"}}