{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QOD7QMQSLKHIXMSNIA3CRTMBTW","short_pith_number":"pith:QOD7QMQS","canonical_record":{"source":{"id":"2508.19724","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T09:34:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"766f35e84f57559d7c0a85d1d5449198fe4239d57f2eb1495b5a66b558611242","abstract_canon_sha256":"cc5604c7b634d6876d3f8fe168e3bcf8359edd18e45c214285ee26160dfaf74f"},"schema_version":"1.0"},"canonical_sha256":"8387f832125a8e8bb24d403628cd819da47f8868675465e620bfe30c0ed1329e","source":{"kind":"arxiv","id":"2508.19724","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19724","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19724v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19724","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"QOD7QMQSLKHI","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"QOD7QMQSLKHIXMSN","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"QOD7QMQS","created_at":"2026-07-05T12:00:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QOD7QMQSLKHIXMSNIA3CRTMBTW","target":"record","payload":{"canonical_record":{"source":{"id":"2508.19724","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T09:34:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"766f35e84f57559d7c0a85d1d5449198fe4239d57f2eb1495b5a66b558611242","abstract_canon_sha256":"cc5604c7b634d6876d3f8fe168e3bcf8359edd18e45c214285ee26160dfaf74f"},"schema_version":"1.0"},"canonical_sha256":"8387f832125a8e8bb24d403628cd819da47f8868675465e620bfe30c0ed1329e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:52.398500Z","signature_b64":"ZKwBpa+8P0pdHOlBTmxDLxSdkOSD9uV9Ftn1eIl1W7Fd+Kan3CLqvtJG9YH5FkWKpzfIU/ipnUbFp73/a1RNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8387f832125a8e8bb24d403628cd819da47f8868675465e620bfe30c0ed1329e","last_reissued_at":"2026-07-05T12:00:52.398005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:52.398005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.19724","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+DuXC9R8hToEdrd3CL8T9XXxAbtgcOUkd0XeniNgLQsDaqsLSEXybYbkD+3jWSmywJEPimWrr2FzQehxc0yoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:05:31.005462Z"},"content_sha256":"b94a843a8e5149427b6f29c1e094cbe5d5d0d7fa2ab827433f8c770dddcf42e4","schema_version":"1.0","event_id":"sha256:b94a843a8e5149427b6f29c1e094cbe5d5d0d7fa2ab827433f8c770dddcf42e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QOD7QMQSLKHIXMSNIA3CRTMBTW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aritra Dutta, Deepanway Ghosal, Somak Aditya, Swapnanil Mukherjee","submitted_at":"2025-08-27T09:34:28Z","abstract_excerpt":"Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language facts, (ii) prompts an LLM to craft natural language explanations, and (iii) feeds both signals to sVLMs respectively across two commonsense VQA datasets (CRIC, AOKVQA) and a visual-entailment dataset (e-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19724","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/2508.19724/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":"2026-07-05T12:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duMVjLpmGQ+VePZpLJyBa9d8Rz11T+Al8VwbT0XGrKNaIdHIWqYe7k54SpQVQeiUp/qn5ldPFRm1zYJYmUB0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:05:31.005956Z"},"content_sha256":"e7d8b1ea24dd00692a52495d2dc8337dbc2b952ff403520f9e4e569ec5066137","schema_version":"1.0","event_id":"sha256:e7d8b1ea24dd00692a52495d2dc8337dbc2b952ff403520f9e4e569ec5066137"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW/bundle.json","state_url":"https://pith.science/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW/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":"2026-08-06T17:05:31Z","links":{"resolver":"https://pith.science/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW","bundle":"https://pith.science/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW/bundle.json","state":"https://pith.science/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOD7QMQSLKHIXMSNIA3CRTMBTW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QOD7QMQSLKHIXMSNIA3CRTMBTW","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":"cc5604c7b634d6876d3f8fe168e3bcf8359edd18e45c214285ee26160dfaf74f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T09:34:28Z","title_canon_sha256":"766f35e84f57559d7c0a85d1d5449198fe4239d57f2eb1495b5a66b558611242"},"schema_version":"1.0","source":{"id":"2508.19724","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19724","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19724v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19724","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"QOD7QMQSLKHI","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"QOD7QMQSLKHIXMSN","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"QOD7QMQS","created_at":"2026-07-05T12:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:e7d8b1ea24dd00692a52495d2dc8337dbc2b952ff403520f9e4e569ec5066137","target":"graph","created_at":"2026-07-05T12:00:52Z","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/2508.19724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language facts, (ii) prompts an LLM to craft natural language explanations, and (iii) feeds both signals to sVLMs respectively across two commonsense VQA datasets (CRIC, AOKVQA) and a visual-entailment dataset (e-","authors_text":"Aritra Dutta, Deepanway Ghosal, Somak Aditya, Swapnanil Mukherjee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T09:34:28Z","title":"NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19724","kind":"arxiv","version":2},"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:b94a843a8e5149427b6f29c1e094cbe5d5d0d7fa2ab827433f8c770dddcf42e4","target":"record","created_at":"2026-07-05T12:00:52Z","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":"cc5604c7b634d6876d3f8fe168e3bcf8359edd18e45c214285ee26160dfaf74f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T09:34:28Z","title_canon_sha256":"766f35e84f57559d7c0a85d1d5449198fe4239d57f2eb1495b5a66b558611242"},"schema_version":"1.0","source":{"id":"2508.19724","kind":"arxiv","version":2}},"canonical_sha256":"8387f832125a8e8bb24d403628cd819da47f8868675465e620bfe30c0ed1329e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8387f832125a8e8bb24d403628cd819da47f8868675465e620bfe30c0ed1329e","first_computed_at":"2026-07-05T12:00:52.398005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:52.398005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZKwBpa+8P0pdHOlBTmxDLxSdkOSD9uV9Ftn1eIl1W7Fd+Kan3CLqvtJG9YH5FkWKpzfIU/ipnUbFp73/a1RNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:52.398500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19724","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b94a843a8e5149427b6f29c1e094cbe5d5d0d7fa2ab827433f8c770dddcf42e4","sha256:e7d8b1ea24dd00692a52495d2dc8337dbc2b952ff403520f9e4e569ec5066137"],"state_sha256":"ed8424ceea64c00542c523670c4d0bad4e5e408fda857656695dd21cc28e3d1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFWNmE1jxVwaakcNacl9zeQAykV32Q1mbhMWuKk1ioqhFWNYELWd09VkiV3Ho4/j0weC+w+MwBGdHZFEBTorBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:05:31.010613Z","bundle_sha256":"d0f8308fab4bd314480faddcbd3e056342956b82e9c4f1dd3334804e70e2d35c"}}