{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UXUYQNEUMK5IWJ7QJNGI4EQPNB","short_pith_number":"pith:UXUYQNEU","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"},"canonical_sha256":"a5e988349462ba8b27f04b4c8e120f6875bc9fb4577fff2c7f8ce70acc138ac1","source":{"kind":"arxiv","id":"2507.21246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21246","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21246v1","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21246","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"UXUYQNEUMK5I","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"UXUYQNEUMK5IWJ7Q","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"UXUYQNEU","created_at":"2026-07-05T11:44:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UXUYQNEUMK5IWJ7QJNGI4EQPNB","target":"record","payload":{"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"},"canonical_sha256":"a5e988349462ba8b27f04b4c8e120f6875bc9fb4577fff2c7f8ce70acc138ac1","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"},"source_kind":"arxiv","source_id":"2507.21246","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":"2026-07-05T11:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmYzBPTauwaMAct0PuSEEi/4/ZOKU7E89CvgR0sKy87kiKO6Un+E2lQNQ40lKxS2Vnyr8DpJukejBT4M+3NWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:00:13.413198Z"},"content_sha256":"3de6fef71bb50a2f1f7b886b3e12a00ccd10933c036e50f0a908a4fa95c672b8","schema_version":"1.0","event_id":"sha256:3de6fef71bb50a2f1f7b886b3e12a00ccd10933c036e50f0a908a4fa95c672b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UXUYQNEUMK5IWJ7QJNGI4EQPNB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ExT63QLZeW1Cf6GzKKCqtrln8evwlH++cYBQphPfCQjxqsCpKFbsrcnPdkdzjueUatb4VqckZict5thscoXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:00:13.413854Z"},"content_sha256":"0586e341ee0bae75ba41ee8b4553c37e78af991d1506ec66539f764100b27076","schema_version":"1.0","event_id":"sha256:0586e341ee0bae75ba41ee8b4553c37e78af991d1506ec66539f764100b27076"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/bundle.json","state_url":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/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":"2026-08-12T10:00:13Z","links":{"resolver":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB","bundle":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/bundle.json","state":"https://pith.science/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXUYQNEUMK5IWJ7QJNGI4EQPNB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UXUYQNEUMK5IWJ7QJNGI4EQPNB","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":"5226ecc2ae8ab00ce089224c74cf2a672e340d06f431705eaec4faacc2223661","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T18:07:30Z","title_canon_sha256":"5fab7e2e43caaed955741e8fdd52b5abe8926c4e7568c6736ddd4bd3b2bd98da"},"schema_version":"1.0","source":{"id":"2507.21246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21246","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21246v1","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21246","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"UXUYQNEUMK5I","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"UXUYQNEUMK5IWJ7Q","created_at":"2026-07-05T11:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"UXUYQNEU","created_at":"2026-07-05T11:44:55Z"}],"graph_snapshots":[{"event_id":"sha256:0586e341ee0bae75ba41ee8b4553c37e78af991d1506ec66539f764100b27076","target":"graph","created_at":"2026-07-05T11:44:55Z","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/2507.21246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Deepak Venugopal, Monika Shah, Somdeb Sarkhel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T18:07:30Z","title":"On Explaining Visual Captioning with Hybrid Markov Logic Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21246","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":"sha256:3de6fef71bb50a2f1f7b886b3e12a00ccd10933c036e50f0a908a4fa95c672b8","target":"record","created_at":"2026-07-05T11:44:55Z","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":"5226ecc2ae8ab00ce089224c74cf2a672e340d06f431705eaec4faacc2223661","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T18:07:30Z","title_canon_sha256":"5fab7e2e43caaed955741e8fdd52b5abe8926c4e7568c6736ddd4bd3b2bd98da"},"schema_version":"1.0","source":{"id":"2507.21246","kind":"arxiv","version":1}},"canonical_sha256":"a5e988349462ba8b27f04b4c8e120f6875bc9fb4577fff2c7f8ce70acc138ac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5e988349462ba8b27f04b4c8e120f6875bc9fb4577fff2c7f8ce70acc138ac1","first_computed_at":"2026-07-05T11:44:55.581746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:55.581746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tI7TNPKPkRrC9/C2LI8qsRhrVJm/oTTmvlOtfU5IyIHP7iKFDGll5QQ6wZ5b3r1995rHYfJTxndYpUcXkrUtAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:55.582252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3de6fef71bb50a2f1f7b886b3e12a00ccd10933c036e50f0a908a4fa95c672b8","sha256:0586e341ee0bae75ba41ee8b4553c37e78af991d1506ec66539f764100b27076"],"state_sha256":"bf232af026011dd3b79802b31dc7a90c9ab55c52c3f538327cdf3bbb130e8ad1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvhiNRugEXd/PEavlTACT9IGIp+U0gKwzJlzNBlz07rEEijDuMbaM33YlmA7A/F5guyMAcRrBsRCkcEv+B+LBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T10:00:13.420532Z","bundle_sha256":"5a0b2121142772b0a551fcb5826d77d34aa4bd6347e93f5e09f6def7d964d15d"}}