{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MBXAMO3PSBCDLYU5ETXU4UTLWE","short_pith_number":"pith:MBXAMO3P","schema_version":"1.0","canonical_sha256":"606e063b6f904435e29d24ef4e526bb12a1fd3a4e938c0e0a53ef0dd1749fc0e","source":{"kind":"arxiv","id":"2310.04981","version":2},"attestation_state":"computed","paper":{"title":"Compositional Semantics for Open Vocabulary Spatio-semantic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Francisco Lepe-Salazar, Kazuya Takeda, Robin Karlsson","submitted_at":"2023-10-08T03:07:14Z","abstract_excerpt":"Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex tasks often requires reasoning about information beyond what is currently perceived. We propose latent compositional semantic embeddings z* as a principled learning-based knowledge representation for queryable spatio-semantic memories. We mathematically prove that z* can always be found, and that the optimal z* is the centroid for any set Z. We derive a probabilistic bound for estimating separability of related and unrelated semantics. We prove that z* "},"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":"2310.04981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T03:07:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"383f861656879b691a7d4c571b38704824307367d82408dbad0e5ca8b66f826c","abstract_canon_sha256":"01861927f70673326b8c61ef9d1f8d2f50f9bdd7e06f5ce38e1e9d7bdcad8e92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:24.629556Z","signature_b64":"LmqI0ZshJdAv5mbviC229KZxLMDvveW1w386Jx00ad7n6vNPxi77Y86JZ4jnUl1NCAJQQfa87XFOhtITpNuKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606e063b6f904435e29d24ef4e526bb12a1fd3a4e938c0e0a53ef0dd1749fc0e","last_reissued_at":"2026-05-26T01:02:24.628710Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:24.628710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Semantics for Open Vocabulary Spatio-semantic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Francisco Lepe-Salazar, Kazuya Takeda, Robin Karlsson","submitted_at":"2023-10-08T03:07:14Z","abstract_excerpt":"Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex tasks often requires reasoning about information beyond what is currently perceived. We propose latent compositional semantic embeddings z* as a principled learning-based knowledge representation for queryable spatio-semantic memories. We mathematically prove that z* can always be found, and that the optimal z* is the centroid for any set Z. We derive a probabilistic bound for estimating separability of related and unrelated semantics. We prove that z* "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04981","kind":"arxiv","version":2},"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/2310.04981/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":"2310.04981","created_at":"2026-05-26T01:02:24.628832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04981v2","created_at":"2026-05-26T01:02:24.628832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04981","created_at":"2026-05-26T01:02:24.628832+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBXAMO3PSBCD","created_at":"2026-05-26T01:02:24.628832+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBXAMO3PSBCDLYU5","created_at":"2026-05-26T01:02:24.628832+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBXAMO3P","created_at":"2026-05-26T01:02:24.628832+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/MBXAMO3PSBCDLYU5ETXU4UTLWE","json":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE.json","graph_json":"https://pith.science/api/pith-number/MBXAMO3PSBCDLYU5ETXU4UTLWE/graph.json","events_json":"https://pith.science/api/pith-number/MBXAMO3PSBCDLYU5ETXU4UTLWE/events.json","paper":"https://pith.science/paper/MBXAMO3P"},"agent_actions":{"view_html":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE","download_json":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE.json","view_paper":"https://pith.science/paper/MBXAMO3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04981&json=true","fetch_graph":"https://pith.science/api/pith-number/MBXAMO3PSBCDLYU5ETXU4UTLWE/graph.json","fetch_events":"https://pith.science/api/pith-number/MBXAMO3PSBCDLYU5ETXU4UTLWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE/action/storage_attestation","attest_author":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE/action/author_attestation","sign_citation":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE/action/citation_signature","submit_replication":"https://pith.science/pith/MBXAMO3PSBCDLYU5ETXU4UTLWE/action/replication_record"}},"created_at":"2026-05-26T01:02:24.628832+00:00","updated_at":"2026-05-26T01:02:24.628832+00:00"}