{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QJ27CRKDG7PTALNRHIAS74X722","short_pith_number":"pith:QJ27CRKD","canonical_record":{"source":{"id":"2412.14672","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:24:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"27eaaf1c97876cda94f2fad0225e57d1e0fc40eb2f6de628a194aff7d0916c87","abstract_canon_sha256":"285cb682668c966d7c4a2331030d98b4bff337eed9bdc7aa847f02d4db9721b2"},"schema_version":"1.0"},"canonical_sha256":"8275f1454337df302db13a012ff2ffd68471483ee1455b6dc24cb3606cadbc39","source":{"kind":"arxiv","id":"2412.14672","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14672","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14672v2","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14672","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"QJ27CRKDG7PT","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"QJ27CRKDG7PTALNR","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"QJ27CRKD","created_at":"2026-07-05T10:34:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QJ27CRKDG7PTALNRHIAS74X722","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14672","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:24:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"27eaaf1c97876cda94f2fad0225e57d1e0fc40eb2f6de628a194aff7d0916c87","abstract_canon_sha256":"285cb682668c966d7c4a2331030d98b4bff337eed9bdc7aa847f02d4db9721b2"},"schema_version":"1.0"},"canonical_sha256":"8275f1454337df302db13a012ff2ffd68471483ee1455b6dc24cb3606cadbc39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:41.893136Z","signature_b64":"ar27qy66sq3QLDfl8DRoB7AOsmertXowpqNwUKuJWO6sizjo0PNj91I/F+GycNFy0TnwuYIA6TbRUGI0BibPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8275f1454337df302db13a012ff2ffd68471483ee1455b6dc24cb3606cadbc39","last_reissued_at":"2026-07-05T10:34:41.892255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:41.892255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14672","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":"2026-07-05T10:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xur9VcvTxv9UNuQld3RrgcFXwlALlpdazPiLjXih61VdHuXtL2TvTuAaE3glsWHFBhnppUw2e2n3jI3zYDoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:47:29.525044Z"},"content_sha256":"7dc504db58f80a7084788df6d572f0390808a2e6e9daf0d2d73c2da8e5f32641","schema_version":"1.0","event_id":"sha256:7dc504db58f80a7084788df6d572f0390808a2e6e9daf0d2d73c2da8e5f32641"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QJ27CRKDG7PTALNRHIAS74X722","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Estelle Aflalo, Gabriela Ben Melech Stan, Man Luo, Sayak Paul, Shachar Rosenman, Shao-Yen Tseng, Tiep Le, Vasudev Lal","submitted_at":"2024-12-19T09:24:10Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as linguistic content when both modalities are necessary to formulate an accurate answer. We hypothesize that hallucinations arise due to the lack of effective visual grounding in current LVLMs. Furthermore, current vision-language benchmarks are not specifically measuring the degree to which the answer require the visual input. This limitation makes it challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14672","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/2412.14672/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":"2026-07-05T10:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2s4HTz1WHPZb6M5BUn28+UVn3NBfQR7gYi0Ak8jfChomL/O5AFWoUf0GI+1Qr9lwkJxA+pq5mIEH00x3DC1rAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:47:29.525429Z"},"content_sha256":"ecc2ba95d6eb573a886d68e2ccfb125458a71914311f1b61adc46468bb49f9c0","schema_version":"1.0","event_id":"sha256:ecc2ba95d6eb573a886d68e2ccfb125458a71914311f1b61adc46468bb49f9c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJ27CRKDG7PTALNRHIAS74X722/bundle.json","state_url":"https://pith.science/pith/QJ27CRKDG7PTALNRHIAS74X722/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJ27CRKDG7PTALNRHIAS74X722/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":"2026-07-07T02:47:29Z","links":{"resolver":"https://pith.science/pith/QJ27CRKDG7PTALNRHIAS74X722","bundle":"https://pith.science/pith/QJ27CRKDG7PTALNRHIAS74X722/bundle.json","state":"https://pith.science/pith/QJ27CRKDG7PTALNRHIAS74X722/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJ27CRKDG7PTALNRHIAS74X722/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QJ27CRKDG7PTALNRHIAS74X722","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":"285cb682668c966d7c4a2331030d98b4bff337eed9bdc7aa847f02d4db9721b2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:24:10Z","title_canon_sha256":"27eaaf1c97876cda94f2fad0225e57d1e0fc40eb2f6de628a194aff7d0916c87"},"schema_version":"1.0","source":{"id":"2412.14672","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14672","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14672v2","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14672","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"QJ27CRKDG7PT","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"QJ27CRKDG7PTALNR","created_at":"2026-07-05T10:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"QJ27CRKD","created_at":"2026-07-05T10:34:41Z"}],"graph_snapshots":[{"event_id":"sha256:ecc2ba95d6eb573a886d68e2ccfb125458a71914311f1b61adc46468bb49f9c0","target":"graph","created_at":"2026-07-05T10:34:41Z","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/2412.14672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as linguistic content when both modalities are necessary to formulate an accurate answer. We hypothesize that hallucinations arise due to the lack of effective visual grounding in current LVLMs. Furthermore, current vision-language benchmarks are not specifically measuring the degree to which the answer require the visual input. This limitation makes it challen","authors_text":"Estelle Aflalo, Gabriela Ben Melech Stan, Man Luo, Sayak Paul, Shachar Rosenman, Shao-Yen Tseng, Tiep Le, Vasudev Lal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:24:10Z","title":"FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14672","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":"sha256:7dc504db58f80a7084788df6d572f0390808a2e6e9daf0d2d73c2da8e5f32641","target":"record","created_at":"2026-07-05T10:34:41Z","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":"285cb682668c966d7c4a2331030d98b4bff337eed9bdc7aa847f02d4db9721b2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:24:10Z","title_canon_sha256":"27eaaf1c97876cda94f2fad0225e57d1e0fc40eb2f6de628a194aff7d0916c87"},"schema_version":"1.0","source":{"id":"2412.14672","kind":"arxiv","version":2}},"canonical_sha256":"8275f1454337df302db13a012ff2ffd68471483ee1455b6dc24cb3606cadbc39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8275f1454337df302db13a012ff2ffd68471483ee1455b6dc24cb3606cadbc39","first_computed_at":"2026-07-05T10:34:41.892255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:41.892255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ar27qy66sq3QLDfl8DRoB7AOsmertXowpqNwUKuJWO6sizjo0PNj91I/F+GycNFy0TnwuYIA6TbRUGI0BibPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:41.893136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14672","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc504db58f80a7084788df6d572f0390808a2e6e9daf0d2d73c2da8e5f32641","sha256:ecc2ba95d6eb573a886d68e2ccfb125458a71914311f1b61adc46468bb49f9c0"],"state_sha256":"86da951a4a0952e526604126beeda20b931244963d0aaf60ab32a2b627d3b522"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8V51cJPHGI+iH+wUdQO+tB43/Q7+rI1IGUuOFEYfuhdFCLVn7n7D+VwIme1O+3Cfx48tiP38e7MsKcbQPQljDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:47:29.527404Z","bundle_sha256":"69869642d6ca199217f1049711b1fc3830ed509a486e6ceea0977d523fcb5637"}}