{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DG6FOX2Q52XD6SQUY5JJILXO37","short_pith_number":"pith:DG6FOX2Q","canonical_record":{"source":{"id":"1807.01448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-04T04:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"b8e8c0e0f3bca496676810be8ab7d74ff4b372abc53633d52e6880c0f1f83d91","abstract_canon_sha256":"2ff343ea8bea3a27a7592edbbb61cd95da83f7db1c24ebe3b7bd61a1227ff63f"},"schema_version":"1.0"},"canonical_sha256":"19bc575f50eeae3f4a14c752942eeedfd8208274e97bc690d267d60060be110b","source":{"kind":"arxiv","id":"1807.01448","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01448","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01448v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01448","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"DG6FOX2Q52XD","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DG6FOX2Q52XD6SQU","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DG6FOX2Q","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DG6FOX2Q52XD6SQUY5JJILXO37","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-04T04:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"b8e8c0e0f3bca496676810be8ab7d74ff4b372abc53633d52e6880c0f1f83d91","abstract_canon_sha256":"2ff343ea8bea3a27a7592edbbb61cd95da83f7db1c24ebe3b7bd61a1227ff63f"},"schema_version":"1.0"},"canonical_sha256":"19bc575f50eeae3f4a14c752942eeedfd8208274e97bc690d267d60060be110b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:29.656982Z","signature_b64":"vnwPlYDG8gaIYY8HcShWpEn/6Bgzyme+nlV/YT1B9uA+vJGvwrn007LabaVdwg9stQLwpLikvjVYanYEDeLhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19bc575f50eeae3f4a14c752942eeedfd8208274e97bc690d267d60060be110b","last_reissued_at":"2026-05-18T00:11:29.656542Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:29.656542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01448","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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4c9YV16akr/+TRsAR+pGVixJYAs/W235XEZJN9GT2eAd8Mt+eMztoACcH/nJ+Txg23+qfVBeYQNowJOBa+B5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:01:37.117424Z"},"content_sha256":"aa665dbec2cb9837de2c81124c00b8e2b06526cf90a0e45892af703adf3fd8cf","schema_version":"1.0","event_id":"sha256:aa665dbec2cb9837de2c81124c00b8e2b06526cf90a0e45892af703adf3fd8cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DG6FOX2Q52XD6SQUY5JJILXO37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Visual Ads by Aligning Symbols and Objects using Co-Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajay Divakaran, Anirban Roy, Karan Sikka, Karuna Ahuja","submitted_at":"2018-07-04T04:50:09Z","abstract_excerpt":"We tackle the problem of understanding visual ads where given an ad image, our goal is to rank appropriate human generated statements describing the purpose of the ad. This problem is generally addressed by jointly embedding images and candidate statements to establish correspondence. Decoding a visual ad requires inference of both semantic and symbolic nuances referenced in an image and prior methods may fail to capture such associations especially with weakly annotated symbols. In order to create better embeddings, we leverage an attention mechanism to associate image proposals with symbols "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01448","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":""},"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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TAbXbcPYieRrRHLG4qiECDj0jGjLxa2ZMlxBcM65Jyr8lIHcK0GqXsCK1wmKG0m6dE2W7i6yz4JP84Jd/fWEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:01:37.117789Z"},"content_sha256":"7fc948706bb291fe7198609780ea7b352c13afd5184f1701e0e7b9e1a856634b","schema_version":"1.0","event_id":"sha256:7fc948706bb291fe7198609780ea7b352c13afd5184f1701e0e7b9e1a856634b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DG6FOX2Q52XD6SQUY5JJILXO37/bundle.json","state_url":"https://pith.science/pith/DG6FOX2Q52XD6SQUY5JJILXO37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DG6FOX2Q52XD6SQUY5JJILXO37/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":"2026-06-02T20:01:37Z","links":{"resolver":"https://pith.science/pith/DG6FOX2Q52XD6SQUY5JJILXO37","bundle":"https://pith.science/pith/DG6FOX2Q52XD6SQUY5JJILXO37/bundle.json","state":"https://pith.science/pith/DG6FOX2Q52XD6SQUY5JJILXO37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DG6FOX2Q52XD6SQUY5JJILXO37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DG6FOX2Q52XD6SQUY5JJILXO37","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":"2ff343ea8bea3a27a7592edbbb61cd95da83f7db1c24ebe3b7bd61a1227ff63f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-04T04:50:09Z","title_canon_sha256":"b8e8c0e0f3bca496676810be8ab7d74ff4b372abc53633d52e6880c0f1f83d91"},"schema_version":"1.0","source":{"id":"1807.01448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01448","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01448v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01448","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"DG6FOX2Q52XD","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DG6FOX2Q52XD6SQU","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DG6FOX2Q","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:7fc948706bb291fe7198609780ea7b352c13afd5184f1701e0e7b9e1a856634b","target":"graph","created_at":"2026-05-18T00:11:29Z","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"},"paper":{"abstract_excerpt":"We tackle the problem of understanding visual ads where given an ad image, our goal is to rank appropriate human generated statements describing the purpose of the ad. This problem is generally addressed by jointly embedding images and candidate statements to establish correspondence. Decoding a visual ad requires inference of both semantic and symbolic nuances referenced in an image and prior methods may fail to capture such associations especially with weakly annotated symbols. In order to create better embeddings, we leverage an attention mechanism to associate image proposals with symbols ","authors_text":"Ajay Divakaran, Anirban Roy, Karan Sikka, Karuna Ahuja","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-04T04:50:09Z","title":"Understanding Visual Ads by Aligning Symbols and Objects using Co-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01448","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:aa665dbec2cb9837de2c81124c00b8e2b06526cf90a0e45892af703adf3fd8cf","target":"record","created_at":"2026-05-18T00:11:29Z","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":"2ff343ea8bea3a27a7592edbbb61cd95da83f7db1c24ebe3b7bd61a1227ff63f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-04T04:50:09Z","title_canon_sha256":"b8e8c0e0f3bca496676810be8ab7d74ff4b372abc53633d52e6880c0f1f83d91"},"schema_version":"1.0","source":{"id":"1807.01448","kind":"arxiv","version":1}},"canonical_sha256":"19bc575f50eeae3f4a14c752942eeedfd8208274e97bc690d267d60060be110b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19bc575f50eeae3f4a14c752942eeedfd8208274e97bc690d267d60060be110b","first_computed_at":"2026-05-18T00:11:29.656542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:29.656542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vnwPlYDG8gaIYY8HcShWpEn/6Bgzyme+nlV/YT1B9uA+vJGvwrn007LabaVdwg9stQLwpLikvjVYanYEDeLhAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:29.656982Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa665dbec2cb9837de2c81124c00b8e2b06526cf90a0e45892af703adf3fd8cf","sha256:7fc948706bb291fe7198609780ea7b352c13afd5184f1701e0e7b9e1a856634b"],"state_sha256":"9962a5ea6ac5fc792c2d9d7c05e8d18d7fbf9ac7eb204645f5aada566c737539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kacUxyVCLGUiNdTLg/rD+PbSyyqIyzEFyLopyFJ4MdGTmyWkgzlX4jlOfE1WL6XTBSVbI55rdVUvNPUvFzh5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:01:37.119841Z","bundle_sha256":"3d6deb24cfb352fa1c687cdb13e89d92aed6f7e4181c0000ab002665a335e786"}}