{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UXUYQNEUMK5IWJ7QJNGI4EQPNB","short_pith_number":"pith:UXUYQNEU","schema_version":"1.0","canonical_sha256":"a5e988349462ba8b27f04b4c8e120f6875bc9fb4577fff2c7f8ce70acc138ac1","source":{"kind":"arxiv","id":"2507.21246","version":1},"attestation_state":"computed","paper":{"title":"On Explaining Visual Captioning with Hybrid Markov Logic Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Deepak Venugopal, Monika Shah, Somdeb Sarkhel","submitted_at":"2025-07-28T18:07:30Z","abstract_excerpt":"Deep Neural Networks (DNNs) have made tremendous progress in multimodal tasks such as image captioning. However, explaining/interpreting how these models integrate visual information, language information and knowledge representation to generate meaningful captions remains a challenging problem. Standard metrics to measure performance typically rely on comparing generated captions with human-written ones that may not provide a user with a deep insights into this integration. In this work, we develop a novel explanation framework that is easily interpretable based on Hybrid Markov Logic Network"},"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":"2507.21246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T18:07:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fab7e2e43caaed955741e8fdd52b5abe8926c4e7568c6736ddd4bd3b2bd98da","abstract_canon_sha256":"5226ecc2ae8ab00ce089224c74cf2a672e340d06f431705eaec4faacc2223661"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:55.582252Z","signature_b64":"tI7TNPKPkRrC9/C2LI8qsRhrVJm/oTTmvlOtfU5IyIHP7iKFDGll5QQ6wZ5b3r1995rHYfJTxndYpUcXkrUtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5e988349462ba8b27f04b4c8e120f6875bc9fb4577fff2c7f8ce70acc138ac1","last_reissued_at":"2026-07-05T11:44:55.581746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:55.581746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Explaining Visual Captioning with Hybrid Markov Logic Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Deepak Venugopal, Monika Shah, Somdeb Sarkhel","submitted_at":"2025-07-28T18:07:30Z","abstract_excerpt":"Deep Neural Networks (DNNs) have made tremendous progress in multimodal tasks such as image captioning. However, explaining/interpreting how these models integrate visual information, language information and knowledge representation to generate meaningful captions remains a challenging problem. Standard metrics to measure performance typically rely on comparing generated captions with human-written ones that may not provide a user with a deep insights into this integration. In this work, we develop a novel explanation framework that is easily interpretable based on Hybrid Markov Logic Network"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21246","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/2507.21246/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":"2507.21246","created_at":"2026-07-05T11:44:55.581801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21246v1","created_at":"2026-07-05T11:44:55.581801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21246","created_at":"2026-07-05T11:44:55.581801+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXUYQNEUMK5I","created_at":"2026-07-05T11:44:55.581801+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXUYQNEUMK5IWJ7Q","created_at":"2026-07-05T11:44:55.581801+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXUYQNEU","created_at":"2026-07-05T11:44:55.581801+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/UXUYQNEUMK5IWJ7QJNGI4EQPNB","json":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB.json","graph_json":"https://pith.science/api/pith-number/UXUYQNEUMK5IWJ7QJNGI4EQPNB/graph.json","events_json":"https://pith.science/api/pith-number/UXUYQNEUMK5IWJ7QJNGI4EQPNB/events.json","paper":"https://pith.science/paper/UXUYQNEU"},"agent_actions":{"view_html":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB","download_json":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB.json","view_paper":"https://pith.science/paper/UXUYQNEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21246&json=true","fetch_graph":"https://pith.science/api/pith-number/UXUYQNEUMK5IWJ7QJNGI4EQPNB/graph.json","fetch_events":"https://pith.science/api/pith-number/UXUYQNEUMK5IWJ7QJNGI4EQPNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/action/storage_attestation","attest_author":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/action/author_attestation","sign_citation":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/action/citation_signature","submit_replication":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/action/replication_record"}},"created_at":"2026-07-05T11:44:55.581801+00:00","updated_at":"2026-07-05T11:44:55.581801+00:00"}