{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X24HZTKIYDKILTV2VHAGAB73JI","short_pith_number":"pith:X24HZTKI","schema_version":"1.0","canonical_sha256":"beb87ccd48c0d485cebaa9c06007fb4a2b59e7cb97d20edc4f61d9952ae1a2bc","source":{"kind":"arxiv","id":"2608.01473","version":1},"attestation_state":"computed","paper":{"title":"Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel A. Hashimoto, Guiqiu Liao, Matjaz Jogan","submitted_at":"2026-08-02T20:09:45Z","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"},"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":"2608.01473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T20:09:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e9376eb2df20a8671da48e3be0e222a8a6aedd92a6554fe7909b099f30c3805a","abstract_canon_sha256":"84506316b75194447daca771b095233ba533d2380ac5cd556097b80a5cce7532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:24.717783Z","signature_b64":"9GZMYxP5TloizqBXK/8F/TszLgXbcj9X1H0ULytfFL3NORzpLaIEy4orcebRT5UpzK9Sdtv/MhSYE64yoffbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beb87ccd48c0d485cebaa9c06007fb4a2b59e7cb97d20edc4f61d9952ae1a2bc","last_reissued_at":"2026-08-04T02:05:24.716126Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:24.716126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel A. Hashimoto, Guiqiu Liao, Matjaz Jogan","submitted_at":"2026-08-02T20:09:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01473","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/2608.01473/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":"2608.01473","created_at":"2026-08-04T02:05:24.717562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01473v1","created_at":"2026-08-04T02:05:24.717562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01473","created_at":"2026-08-04T02:05:24.717562+00:00"},{"alias_kind":"pith_short_12","alias_value":"X24HZTKIYDKI","created_at":"2026-08-04T02:05:24.717562+00:00"},{"alias_kind":"pith_short_16","alias_value":"X24HZTKIYDKILTV2","created_at":"2026-08-04T02:05:24.717562+00:00"},{"alias_kind":"pith_short_8","alias_value":"X24HZTKI","created_at":"2026-08-04T02:05:24.717562+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/X24HZTKIYDKILTV2VHAGAB73JI","json":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI.json","graph_json":"https://pith.science/api/pith-number/X24HZTKIYDKILTV2VHAGAB73JI/graph.json","events_json":"https://pith.science/api/pith-number/X24HZTKIYDKILTV2VHAGAB73JI/events.json","paper":"https://pith.science/paper/X24HZTKI"},"agent_actions":{"view_html":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI","download_json":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI.json","view_paper":"https://pith.science/paper/X24HZTKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01473&json=true","fetch_graph":"https://pith.science/api/pith-number/X24HZTKIYDKILTV2VHAGAB73JI/graph.json","fetch_events":"https://pith.science/api/pith-number/X24HZTKIYDKILTV2VHAGAB73JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI/action/storage_attestation","attest_author":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI/action/author_attestation","sign_citation":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI/action/citation_signature","submit_replication":"https://pith.science/pith/X24HZTKIYDKILTV2VHAGAB73JI/action/replication_record"}},"created_at":"2026-08-04T02:05:24.717562+00:00","updated_at":"2026-08-04T02:05:24.717562+00:00"}