{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AC2I3VWDCOIO2U4ZEVBDVUY6ZP","short_pith_number":"pith:AC2I3VWD","schema_version":"1.0","canonical_sha256":"00b48dd6c31390ed539925423ad31ecbde393f06f437fd02f11c178b1d43704f","source":{"kind":"arxiv","id":"2508.18179","version":1},"attestation_state":"computed","paper":{"title":"SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Ashton Anderson, Blair Yang, Difan Jiao, Zhenwei Tang","submitted_at":"2025-08-25T16:33:07Z","abstract_excerpt":"Evaluating whether vision-language models (VLMs) reason consistently across representations is challenging because modality comparisons are typically confounded by task differences and asymmetric information. We introduce SEAM, a benchmark that pairs semantically equivalent inputs across four domains that have existing standardized textual and visual notations. By employing distinct notation systems across modalities, in contrast to OCR-based image-text pairing, SEAM provides a rigorous comparative assessment of the textual-symbolic and visual-spatial reasoning capabilities of VLMs. Across 21 "},"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":"2508.18179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-25T16:33:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6f0505a9d31e669c2e39a7af3fda78d0ac4f5878bc18d896ef844c0ca86f27dc","abstract_canon_sha256":"97ce3918369c3cfb215461a643f16467646040249d873b80f3d8619f47929d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:55.000293Z","signature_b64":"eZXrOJn9cK91sqqcUT1C8JL/URP8BJkeriXJIL34CzYyvzXBroj8rHmvz+Vf1NrbomZGpMj02ApqdDLkQTVBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00b48dd6c31390ed539925423ad31ecbde393f06f437fd02f11c178b1d43704f","last_reissued_at":"2026-07-05T11:58:54.999833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:54.999833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Ashton Anderson, Blair Yang, Difan Jiao, Zhenwei Tang","submitted_at":"2025-08-25T16:33:07Z","abstract_excerpt":"Evaluating whether vision-language models (VLMs) reason consistently across representations is challenging because modality comparisons are typically confounded by task differences and asymmetric information. We introduce SEAM, a benchmark that pairs semantically equivalent inputs across four domains that have existing standardized textual and visual notations. By employing distinct notation systems across modalities, in contrast to OCR-based image-text pairing, SEAM provides a rigorous comparative assessment of the textual-symbolic and visual-spatial reasoning capabilities of VLMs. Across 21 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18179","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/2508.18179/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":"2508.18179","created_at":"2026-07-05T11:58:54.999897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18179v1","created_at":"2026-07-05T11:58:54.999897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18179","created_at":"2026-07-05T11:58:54.999897+00:00"},{"alias_kind":"pith_short_12","alias_value":"AC2I3VWDCOIO","created_at":"2026-07-05T11:58:54.999897+00:00"},{"alias_kind":"pith_short_16","alias_value":"AC2I3VWDCOIO2U4Z","created_at":"2026-07-05T11:58:54.999897+00:00"},{"alias_kind":"pith_short_8","alias_value":"AC2I3VWD","created_at":"2026-07-05T11:58:54.999897+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/AC2I3VWDCOIO2U4ZEVBDVUY6ZP","json":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP.json","graph_json":"https://pith.science/api/pith-number/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/graph.json","events_json":"https://pith.science/api/pith-number/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/events.json","paper":"https://pith.science/paper/AC2I3VWD"},"agent_actions":{"view_html":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP","download_json":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP.json","view_paper":"https://pith.science/paper/AC2I3VWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18179&json=true","fetch_graph":"https://pith.science/api/pith-number/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/graph.json","fetch_events":"https://pith.science/api/pith-number/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/action/storage_attestation","attest_author":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/action/author_attestation","sign_citation":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/action/citation_signature","submit_replication":"https://pith.science/pith/AC2I3VWDCOIO2U4ZEVBDVUY6ZP/action/replication_record"}},"created_at":"2026-07-05T11:58:54.999897+00:00","updated_at":"2026-07-05T11:58:54.999897+00:00"}