{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TFGVXW22WXN3QJWZSDHQS76LE5","short_pith_number":"pith:TFGVXW22","canonical_record":{"source":{"id":"2505.24208","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T04:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"adff9903f5ff9dc5ddc6a22cb11fd5f7cb63d187983c7212f18df781d542e29d","abstract_canon_sha256":"e6d80481ec1b2d839f66548092a3136264cfcb87e0c99049889a596c42fe224c"},"schema_version":"1.0"},"canonical_sha256":"994d5bdb5ab5dbb826d990cf097fcb2746e2da215059b02eee4c5f9dba87ed6d","source":{"kind":"arxiv","id":"2505.24208","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24208","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24208v1","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24208","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"TFGVXW22WXN3","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"TFGVXW22WXN3QJWZ","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"TFGVXW22","created_at":"2026-07-05T11:12:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TFGVXW22WXN3QJWZSDHQS76LE5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24208","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T04:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"adff9903f5ff9dc5ddc6a22cb11fd5f7cb63d187983c7212f18df781d542e29d","abstract_canon_sha256":"e6d80481ec1b2d839f66548092a3136264cfcb87e0c99049889a596c42fe224c"},"schema_version":"1.0"},"canonical_sha256":"994d5bdb5ab5dbb826d990cf097fcb2746e2da215059b02eee4c5f9dba87ed6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:44.093792Z","signature_b64":"u3ErlWWzScU0BwVjYwqJdBLJ6OXns0exIp7eLOxSOlzovrh/UraDS29voTQguH6z7hPPTzpsCi4U/9EzzcJLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994d5bdb5ab5dbb826d990cf097fcb2746e2da215059b02eee4c5f9dba87ed6d","last_reissued_at":"2026-07-05T11:12:44.093253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:44.093253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24208","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":"2026-07-05T11:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c4NbxD58LFoVXt7zPCVfgGFZUok5poW+gVDD6DGNK4KwDYJ2ZHYO9ocgfJF60+nfmTORVbA7i81+rQwsoFPmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:00:54.372035Z"},"content_sha256":"01901af1a33ecc0117e858d7ae25b35a933973129cdbaa8ce99e850e83190023","schema_version":"1.0","event_id":"sha256:01901af1a33ecc0117e858d7ae25b35a933973129cdbaa8ce99e850e83190023"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TFGVXW22WXN3QJWZSDHQS76LE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ali Payani, Baharan Mirzasoleiman, Spencer Stice, Wenhan Yang","submitted_at":"2025-05-30T04:40:08Z","abstract_excerpt":"Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs to generate harmful responses to prompts that would otherwise be refused in text-only contexts. The modality gap between image and text representations has been recently hypothesized to contribute to safety degradation of LVLMs. However, if and how the amount of modality gap affects LVLMs' safety is not studied. In this work, we show that the amount of modali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24208","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/2505.24208/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":"2026-07-05T11:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dCGN1VpXLiNcGXlUCLqURWE9+6bW3o1o8B0SuSmr9zhUpisaK2mjkUcFzG8ytulql6K6A7nUuho5oogeWABDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:00:54.372623Z"},"content_sha256":"b731de7779dbf1e0fed28d104ef613238bff5388f2c459d42ffc29e43b91c990","schema_version":"1.0","event_id":"sha256:b731de7779dbf1e0fed28d104ef613238bff5388f2c459d42ffc29e43b91c990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFGVXW22WXN3QJWZSDHQS76LE5/bundle.json","state_url":"https://pith.science/pith/TFGVXW22WXN3QJWZSDHQS76LE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFGVXW22WXN3QJWZSDHQS76LE5/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":"2026-08-09T14:00:54Z","links":{"resolver":"https://pith.science/pith/TFGVXW22WXN3QJWZSDHQS76LE5","bundle":"https://pith.science/pith/TFGVXW22WXN3QJWZSDHQS76LE5/bundle.json","state":"https://pith.science/pith/TFGVXW22WXN3QJWZSDHQS76LE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFGVXW22WXN3QJWZSDHQS76LE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TFGVXW22WXN3QJWZSDHQS76LE5","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":"e6d80481ec1b2d839f66548092a3136264cfcb87e0c99049889a596c42fe224c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T04:40:08Z","title_canon_sha256":"adff9903f5ff9dc5ddc6a22cb11fd5f7cb63d187983c7212f18df781d542e29d"},"schema_version":"1.0","source":{"id":"2505.24208","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24208","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24208v1","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24208","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"TFGVXW22WXN3","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"TFGVXW22WXN3QJWZ","created_at":"2026-07-05T11:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"TFGVXW22","created_at":"2026-07-05T11:12:44Z"}],"graph_snapshots":[{"event_id":"sha256:b731de7779dbf1e0fed28d104ef613238bff5388f2c459d42ffc29e43b91c990","target":"graph","created_at":"2026-07-05T11:12:44Z","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/2505.24208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs to generate harmful responses to prompts that would otherwise be refused in text-only contexts. The modality gap between image and text representations has been recently hypothesized to contribute to safety degradation of LVLMs. However, if and how the amount of modality gap affects LVLMs' safety is not studied. In this work, we show that the amount of modali","authors_text":"Ali Payani, Baharan Mirzasoleiman, Spencer Stice, Wenhan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T04:40:08Z","title":"Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24208","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":"sha256:01901af1a33ecc0117e858d7ae25b35a933973129cdbaa8ce99e850e83190023","target":"record","created_at":"2026-07-05T11:12:44Z","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":"e6d80481ec1b2d839f66548092a3136264cfcb87e0c99049889a596c42fe224c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T04:40:08Z","title_canon_sha256":"adff9903f5ff9dc5ddc6a22cb11fd5f7cb63d187983c7212f18df781d542e29d"},"schema_version":"1.0","source":{"id":"2505.24208","kind":"arxiv","version":1}},"canonical_sha256":"994d5bdb5ab5dbb826d990cf097fcb2746e2da215059b02eee4c5f9dba87ed6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"994d5bdb5ab5dbb826d990cf097fcb2746e2da215059b02eee4c5f9dba87ed6d","first_computed_at":"2026-07-05T11:12:44.093253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:44.093253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u3ErlWWzScU0BwVjYwqJdBLJ6OXns0exIp7eLOxSOlzovrh/UraDS29voTQguH6z7hPPTzpsCi4U/9EzzcJLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:44.093792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24208","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01901af1a33ecc0117e858d7ae25b35a933973129cdbaa8ce99e850e83190023","sha256:b731de7779dbf1e0fed28d104ef613238bff5388f2c459d42ffc29e43b91c990"],"state_sha256":"19fae6bcf48fe908b2f7e38504770a4f0e815ff5b206f5e8172fb5492040e17b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"op9wg+MdJiwuXbkdhCE7EW2tEqvnhnYGblZKFNyNQlaro/vEovzP8xfoab8flU+9gDiwuzMRhbmlLPFFunVSCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:00:54.377915Z","bundle_sha256":"00bceede754fe032fed6ab88b29287c5ec7500ec36851f10ae67913f558e4b03"}}