{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2CNMP7OP23AFUXVRTGZHAFNEII","short_pith_number":"pith:2CNMP7OP","schema_version":"1.0","canonical_sha256":"d09ac7fdcfd6c05a5eb199b27015a442277020b0e610d34df33756918992af80","source":{"kind":"arxiv","id":"2305.14410","version":2},"attestation_state":"computed","paper":{"title":"Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Arnab Kumar Mondal, Ashish Goswami, Dinesh Garg, Dinesh Khandelwal, Harman Singh, Kevin Shah, Mohit Gupta, Parag Singla, Poorva Garg, Satyam Modi","submitted_at":"2023-05-23T17:59:10Z","abstract_excerpt":"We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning (NSCL), which has been quite effective for the task of Visual Question Answering (VQA), for the task of image manipulation. Our system referred to as NeuroSIM can perform complex multi-hop reasoning over multi-object scenes and only requires weak supervision in the form of annotated data for VQA. NeuroSIM parses an instruction into a symbolic program, based on a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.14410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T17:59:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0c7d480d7ab18a0fd2af0bed6aa6ef047f827edc6e0c1ee9fc919ace4f5c046a","abstract_canon_sha256":"6bd366c2b864b55e471ec86d19494a9e1d8e9373c23e3863bca4342a1b1d1c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:47.534106Z","signature_b64":"6z1cgOGTWlk6pUKb0ocGvcTO/M+TN5uytQRBvNzdnFE+DKEgbZJwcHnaFI9V6YsgyFLDn7kjKnGTPH1ExrnJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09ac7fdcfd6c05a5eb199b27015a442277020b0e610d34df33756918992af80","last_reissued_at":"2026-07-05T07:04:47.533690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:47.533690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Arnab Kumar Mondal, Ashish Goswami, Dinesh Garg, Dinesh Khandelwal, Harman Singh, Kevin Shah, Mohit Gupta, Parag Singla, Poorva Garg, Satyam Modi","submitted_at":"2023-05-23T17:59:10Z","abstract_excerpt":"We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning (NSCL), which has been quite effective for the task of Visual Question Answering (VQA), for the task of image manipulation. Our system referred to as NeuroSIM can perform complex multi-hop reasoning over multi-object scenes and only requires weak supervision in the form of annotated data for VQA. NeuroSIM parses an instruction into a symbolic program, based on a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14410","kind":"arxiv","version":2},"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/2305.14410/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.14410","created_at":"2026-07-05T07:04:47.533746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14410v2","created_at":"2026-07-05T07:04:47.533746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14410","created_at":"2026-07-05T07:04:47.533746+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CNMP7OP23AF","created_at":"2026-07-05T07:04:47.533746+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CNMP7OP23AFUXVR","created_at":"2026-07-05T07:04:47.533746+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CNMP7OP","created_at":"2026-07-05T07:04:47.533746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII","json":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII.json","graph_json":"https://pith.science/api/pith-number/2CNMP7OP23AFUXVRTGZHAFNEII/graph.json","events_json":"https://pith.science/api/pith-number/2CNMP7OP23AFUXVRTGZHAFNEII/events.json","paper":"https://pith.science/paper/2CNMP7OP"},"agent_actions":{"view_html":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII","download_json":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII.json","view_paper":"https://pith.science/paper/2CNMP7OP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14410&json=true","fetch_graph":"https://pith.science/api/pith-number/2CNMP7OP23AFUXVRTGZHAFNEII/graph.json","fetch_events":"https://pith.science/api/pith-number/2CNMP7OP23AFUXVRTGZHAFNEII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII/action/storage_attestation","attest_author":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII/action/author_attestation","sign_citation":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII/action/citation_signature","submit_replication":"https://pith.science/pith/2CNMP7OP23AFUXVRTGZHAFNEII/action/replication_record"}},"created_at":"2026-07-05T07:04:47.533746+00:00","updated_at":"2026-07-05T07:04:47.533746+00:00"}