{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GPBKENJ2JOLT2FUNBPW2OTLAQP","short_pith_number":"pith:GPBKENJ2","schema_version":"1.0","canonical_sha256":"33c2a2353a4b973d168d0beda74d6083d95f89361123dcdce0da8456c27675be","source":{"kind":"arxiv","id":"2607.17712","version":1},"attestation_state":"computed","paper":{"title":"Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Attention-Based Solution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Mehler, Ali Abusaleh, Leon Hammerla","submitted_at":"2026-07-20T09:08:51Z","abstract_excerpt":"Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies"},"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":"2607.17712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T09:08:51Z","cross_cats_sorted":[],"title_canon_sha256":"35b4c3e7fca97b041980ea460ad69e43e9dbb6c36650e1a9c87ef15415895d5b","abstract_canon_sha256":"ac85b4287216172fa25971818d719f7a1d4d23c8c627a07a3523fef2ca631bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:55.784776Z","signature_b64":"Ung3ipuvNwD/qYZtuPUpnC7FTes2j5i+1+Q56RChK3RHPYDRR84jTBkrYRBomk6ch6D0YwdTEX8ho1+lYkI/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33c2a2353a4b973d168d0beda74d6083d95f89361123dcdce0da8456c27675be","last_reissued_at":"2026-07-21T02:21:55.783788Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:55.783788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Attention-Based Solution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Mehler, Ali Abusaleh, Leon Hammerla","submitted_at":"2026-07-20T09:08:51Z","abstract_excerpt":"Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17712","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/2607.17712/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":"2607.17712","created_at":"2026-07-21T02:21:55.784260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17712v1","created_at":"2026-07-21T02:21:55.784260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17712","created_at":"2026-07-21T02:21:55.784260+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPBKENJ2JOLT","created_at":"2026-07-21T02:21:55.784260+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPBKENJ2JOLT2FUN","created_at":"2026-07-21T02:21:55.784260+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPBKENJ2","created_at":"2026-07-21T02:21:55.784260+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/GPBKENJ2JOLT2FUNBPW2OTLAQP","json":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP.json","graph_json":"https://pith.science/api/pith-number/GPBKENJ2JOLT2FUNBPW2OTLAQP/graph.json","events_json":"https://pith.science/api/pith-number/GPBKENJ2JOLT2FUNBPW2OTLAQP/events.json","paper":"https://pith.science/paper/GPBKENJ2"},"agent_actions":{"view_html":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP","download_json":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP.json","view_paper":"https://pith.science/paper/GPBKENJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17712&json=true","fetch_graph":"https://pith.science/api/pith-number/GPBKENJ2JOLT2FUNBPW2OTLAQP/graph.json","fetch_events":"https://pith.science/api/pith-number/GPBKENJ2JOLT2FUNBPW2OTLAQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP/action/storage_attestation","attest_author":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP/action/author_attestation","sign_citation":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP/action/citation_signature","submit_replication":"https://pith.science/pith/GPBKENJ2JOLT2FUNBPW2OTLAQP/action/replication_record"}},"created_at":"2026-07-21T02:21:55.784260+00:00","updated_at":"2026-07-21T02:21:55.784260+00:00"}