{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OG4AHFUJAFY67XMK4VRARHJVJS","short_pith_number":"pith:OG4AHFUJ","schema_version":"1.0","canonical_sha256":"71b80396890171efdd8ae562089d354c85f868a1c8eb6273a0160c3e9eab614f","source":{"kind":"arxiv","id":"2607.06402","version":1},"attestation_state":"computed","paper":{"title":"What Images Cannot Say: Language-Guided Olfactory Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eleftherios Tsonis, Vicky Kalogeiton, Xi Wang","submitted_at":"2026-07-07T15:31:55Z","abstract_excerpt":"Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent datasets pair visual scenes with electronic-nose measurements, aligning smell signals with images remains challenging because many olfactory cues arise from contextual environmental factors that are not directly visible in pixels. We introduce SCENT, a multimodal framework that uses language guidance as a semantic bridge between vision and olfaction. Our approach leverages Vision-Language Models (VLMs) to generate scene descriptors capturing objects, environmental context, and plausible ambient"},"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":"2607.06402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T15:31:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e0a835fc761800c81be99d06f6643f2379c1016c7af695f9cd893ecccdd38e4","abstract_canon_sha256":"6a49c5662d27d6afd99059fa3ae70b2c43edba61e2f24c0b69996e706d3af245"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:24.345135Z","signature_b64":"9kBVlwvbBnEIvw0caC0DlA1ZUTwbC7JKUsWwbtwHwzwvA1pQMnGvct1LYWedO4GP6wkwVeiTV6AuCMPz4ce4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71b80396890171efdd8ae562089d354c85f868a1c8eb6273a0160c3e9eab614f","last_reissued_at":"2026-07-08T01:19:24.344672Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:24.344672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Images Cannot Say: Language-Guided Olfactory Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eleftherios Tsonis, Vicky Kalogeiton, Xi Wang","submitted_at":"2026-07-07T15:31:55Z","abstract_excerpt":"Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent datasets pair visual scenes with electronic-nose measurements, aligning smell signals with images remains challenging because many olfactory cues arise from contextual environmental factors that are not directly visible in pixels. We introduce SCENT, a multimodal framework that uses language guidance as a semantic bridge between vision and olfaction. Our approach leverages Vision-Language Models (VLMs) to generate scene descriptors capturing objects, environmental context, and plausible ambient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06402","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/2607.06402/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":"2607.06402","created_at":"2026-07-08T01:19:24.344742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06402v1","created_at":"2026-07-08T01:19:24.344742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06402","created_at":"2026-07-08T01:19:24.344742+00:00"},{"alias_kind":"pith_short_12","alias_value":"OG4AHFUJAFY6","created_at":"2026-07-08T01:19:24.344742+00:00"},{"alias_kind":"pith_short_16","alias_value":"OG4AHFUJAFY67XMK","created_at":"2026-07-08T01:19:24.344742+00:00"},{"alias_kind":"pith_short_8","alias_value":"OG4AHFUJ","created_at":"2026-07-08T01:19:24.344742+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/OG4AHFUJAFY67XMK4VRARHJVJS","json":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS.json","graph_json":"https://pith.science/api/pith-number/OG4AHFUJAFY67XMK4VRARHJVJS/graph.json","events_json":"https://pith.science/api/pith-number/OG4AHFUJAFY67XMK4VRARHJVJS/events.json","paper":"https://pith.science/paper/OG4AHFUJ"},"agent_actions":{"view_html":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS","download_json":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS.json","view_paper":"https://pith.science/paper/OG4AHFUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06402&json=true","fetch_graph":"https://pith.science/api/pith-number/OG4AHFUJAFY67XMK4VRARHJVJS/graph.json","fetch_events":"https://pith.science/api/pith-number/OG4AHFUJAFY67XMK4VRARHJVJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS/action/storage_attestation","attest_author":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS/action/author_attestation","sign_citation":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS/action/citation_signature","submit_replication":"https://pith.science/pith/OG4AHFUJAFY67XMK4VRARHJVJS/action/replication_record"}},"created_at":"2026-07-08T01:19:24.344742+00:00","updated_at":"2026-07-08T01:19:24.344742+00:00"}