{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OYBF5OTS6QTGEXWIQZWGLO7PMD","short_pith_number":"pith:OYBF5OTS","canonical_record":{"source":{"id":"2406.11820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"6fb5a15b2cd77be5a14c88c2a75a27dac281fb0a3c0b10760feea23bfd7ab4b6","abstract_canon_sha256":"4026ebb22e2c819f316002bc8d4ba914802d24c1f29064007e2323095515c144"},"schema_version":"1.0"},"canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","source":{"kind":"arxiv","id":"2406.11820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11820","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11820v1","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11820","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"OYBF5OTS6QTG","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"OYBF5OTS6QTGEXWI","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"OYBF5OTS","created_at":"2026-07-05T08:32:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OYBF5OTS6QTGEXWIQZWGLO7PMD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"6fb5a15b2cd77be5a14c88c2a75a27dac281fb0a3c0b10760feea23bfd7ab4b6","abstract_canon_sha256":"4026ebb22e2c819f316002bc8d4ba914802d24c1f29064007e2323095515c144"},"schema_version":"1.0"},"canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:58.301284Z","signature_b64":"bgBqEvgK/IdQdYCPksHoPoTEaIAu6OTGhj3z3fKhl3kUoyX0MDuxNtyCDCM5UMpqlVOx9Z/gJewmuwoFHJmQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","last_reissued_at":"2026-07-05T08:32:58.300870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:58.300870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11820","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":"2026-07-05T08:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lt3lzhgU2uW/yfHKZzJdDuBYRmUQMEA44tdVVDiI6I84ORgHSlB1//K2ZG5NMOVRLZokjXepbWgI4JvaJfMaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:01:34.956520Z"},"content_sha256":"e29c6479ed685fb7b0f060373ee116ce4e14b315dc6e51ffcbdb29961f38f39d","schema_version":"1.0","event_id":"sha256:e29c6479ed685fb7b0f060373ee116ce4e14b315dc6e51ffcbdb29961f38f39d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OYBF5OTS6QTGEXWIQZWGLO7PMD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Composing Object Relations and Attributes for Image-Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Chuong Huynh, Khoi Pham, Ser-Nam Lim","submitted_at":"2024-06-17T17:56:01Z","abstract_excerpt":"We study the visual semantic embedding problem for image-text matching. Most existing work utilizes a tailored cross-attention mechanism to perform local alignment across the two image and text modalities. This is computationally expensive, even though it is more powerful than the unimodal dual-encoder approach. This work introduces a dual-encoder image-text matching model, leveraging a scene graph to represent captions with nodes for objects and attributes interconnected by relational edges. Utilizing a graph attention network, our model efficiently encodes object-attribute and object-object "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11820","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/2406.11820/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":"2026-07-05T08:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gG7YNvstbPtWDbO39kv8aGWByaIBpp7ztuArMiH3pFW3YK3ltMagfbiZCi27dQgxtYzwMHevHYT3roUvdJfcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:01:34.957021Z"},"content_sha256":"790a721f5d2d0f39cbb932dcda9ad168d92dff2d89b7a772393f328296ca945a","schema_version":"1.0","event_id":"sha256:790a721f5d2d0f39cbb932dcda9ad168d92dff2d89b7a772393f328296ca945a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/bundle.json","state_url":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/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":"2026-08-07T18:01:34Z","links":{"resolver":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD","bundle":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/bundle.json","state":"https://pith.science/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYBF5OTS6QTGEXWIQZWGLO7PMD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OYBF5OTS6QTGEXWIQZWGLO7PMD","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":"4026ebb22e2c819f316002bc8d4ba914802d24c1f29064007e2323095515c144","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:56:01Z","title_canon_sha256":"6fb5a15b2cd77be5a14c88c2a75a27dac281fb0a3c0b10760feea23bfd7ab4b6"},"schema_version":"1.0","source":{"id":"2406.11820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11820","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11820v1","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11820","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"OYBF5OTS6QTG","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"OYBF5OTS6QTGEXWI","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"OYBF5OTS","created_at":"2026-07-05T08:32:58Z"}],"graph_snapshots":[{"event_id":"sha256:790a721f5d2d0f39cbb932dcda9ad168d92dff2d89b7a772393f328296ca945a","target":"graph","created_at":"2026-07-05T08:32:58Z","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/2406.11820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the visual semantic embedding problem for image-text matching. Most existing work utilizes a tailored cross-attention mechanism to perform local alignment across the two image and text modalities. This is computationally expensive, even though it is more powerful than the unimodal dual-encoder approach. This work introduces a dual-encoder image-text matching model, leveraging a scene graph to represent captions with nodes for objects and attributes interconnected by relational edges. Utilizing a graph attention network, our model efficiently encodes object-attribute and object-object ","authors_text":"Abhinav Shrivastava, Chuong Huynh, Khoi Pham, Ser-Nam Lim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:56:01Z","title":"Composing Object Relations and Attributes for Image-Text Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11820","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:e29c6479ed685fb7b0f060373ee116ce4e14b315dc6e51ffcbdb29961f38f39d","target":"record","created_at":"2026-07-05T08:32:58Z","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":"4026ebb22e2c819f316002bc8d4ba914802d24c1f29064007e2323095515c144","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:56:01Z","title_canon_sha256":"6fb5a15b2cd77be5a14c88c2a75a27dac281fb0a3c0b10760feea23bfd7ab4b6"},"schema_version":"1.0","source":{"id":"2406.11820","kind":"arxiv","version":1}},"canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76025eba72f426625ec8866c65bbef60d17711b3209f1082d117e328e6dc4c0c","first_computed_at":"2026-07-05T08:32:58.300870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:58.300870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bgBqEvgK/IdQdYCPksHoPoTEaIAu6OTGhj3z3fKhl3kUoyX0MDuxNtyCDCM5UMpqlVOx9Z/gJewmuwoFHJmQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:58.301284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e29c6479ed685fb7b0f060373ee116ce4e14b315dc6e51ffcbdb29961f38f39d","sha256:790a721f5d2d0f39cbb932dcda9ad168d92dff2d89b7a772393f328296ca945a"],"state_sha256":"56ddab17c4fd10407166cddaafbe664ed2ef727f44058cd4e68fb15f959c4170"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9d78eOHeeOuuGefF0rB2Hk+bQ4QWNtYIV4ZeySozkYC/hqOmH38ORYErgKxipEw+KJHIkWLtQMY83BRSfzMDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:01:34.961298Z","bundle_sha256":"b1c5ff9f5bba4c97927c77ced9349b82d427391777e20b49e1c58af7710413a8"}}