{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X24HZTKIYDKILTV2VHAGAB73JI","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":"84506316b75194447daca771b095233ba533d2380ac5cd556097b80a5cce7532","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T20:09:45Z","title_canon_sha256":"e9376eb2df20a8671da48e3be0e222a8a6aedd92a6554fe7909b099f30c3805a"},"schema_version":"1.0","source":{"id":"2608.01473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01473","created_at":"2026-08-04T02:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01473v1","created_at":"2026-08-04T02:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01473","created_at":"2026-08-04T02:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"X24HZTKIYDKI","created_at":"2026-08-04T02:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"X24HZTKIYDKILTV2","created_at":"2026-08-04T02:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"X24HZTKI","created_at":"2026-08-04T02:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:5f0737e12cef879297e87f56004490c57bb42fe4519cb358298592c42f7d5f34","target":"graph","created_at":"2026-08-04T02:05:24Z","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/2608.01473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers. We present Slot2Text, a dual-mode surgical MLLM that replaces dense representations of visual input with a compact set of regions encoded as slot latents. Instead of relying on contrastive alignment of the visual encoder with language, Slot2Text groups self-supervised vision features into a few regions--slots that are consumed by the language model as area-labeled visu","authors_text":"Daniel A. Hashimoto, Guiqiu Liao, Matjaz Jogan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T20:09:45Z","title":"Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01473","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":"sha256:714bc4361cdba9ccf5b884d3ec8af52a77a59e1ddc61c852965e279af1cc13b4","target":"record","created_at":"2026-08-04T02:05:24Z","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":"84506316b75194447daca771b095233ba533d2380ac5cd556097b80a5cce7532","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T20:09:45Z","title_canon_sha256":"e9376eb2df20a8671da48e3be0e222a8a6aedd92a6554fe7909b099f30c3805a"},"schema_version":"1.0","source":{"id":"2608.01473","kind":"arxiv","version":1}},"canonical_sha256":"beb87ccd48c0d485cebaa9c06007fb4a2b59e7cb97d20edc4f61d9952ae1a2bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beb87ccd48c0d485cebaa9c06007fb4a2b59e7cb97d20edc4f61d9952ae1a2bc","first_computed_at":"2026-08-04T02:05:24.716126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:05:24.716126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9GZMYxP5TloizqBXK/8F/TszLgXbcj9X1H0ULytfFL3NORzpLaIEy4orcebRT5UpzK9Sdtv/MhSYE64yoffbDQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:05:24.717783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:714bc4361cdba9ccf5b884d3ec8af52a77a59e1ddc61c852965e279af1cc13b4","sha256:5f0737e12cef879297e87f56004490c57bb42fe4519cb358298592c42f7d5f34"],"state_sha256":"1284472206039fbe87a6ba1caa33751e228e9e87fd8b9ca12e13d00d2257ca2c"}