{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:46HOFOF2J4LLSKHJGPZQGFYHVG","short_pith_number":"pith:46HOFOF2","schema_version":"1.0","canonical_sha256":"e78ee2b8ba4f16b928e933f3031707a99173415137ae8f5033d9434cfdb52c10","source":{"kind":"arxiv","id":"2412.08821","version":2},"attestation_state":"computed","paper":{"title":"Large Concept Models: Language Modeling in a Sentence Representation Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Mourachko, Artyom Kozhevnikov, Belen Alastruey, Christophe Ropers, David Dale, Eduardo S\\'anchez, Guillaume Couairon, Hady Elsahar, Holger Schwenk, Jo\\~ao Maria Janeiro, Kevin Heffernan, LCM team, Lo\\\"ic Barrault, Maha Elbayad, Mariano Coria, Marta R. Costa-juss\\`a, Paul-Ambroise Duquenne, Pierre Andrews, Robin San Roman, Safiyyah Saleem, Tuan Tran","submitted_at":"2024-12-11T23:36:20Z","abstract_excerpt":"LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, well beyond single words, to analyze information and to generate creative content. In this paper, we present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a concept. Concepts are language- and modality-agnostic and represent a highe"},"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":"2412.08821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T23:36:20Z","cross_cats_sorted":[],"title_canon_sha256":"bb65b93f559ea4fba8e916b3ae34305c51d47d82da9091f336fb56b67e2619fb","abstract_canon_sha256":"d0d23f841d8877055f1d5f73f590b1e53dc2e247928ca65a00c9f61d42fb0a2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:14.234851Z","signature_b64":"e2ZWgjV48/9GCTArvuFrYJbF01IZX1M/beazVuRfiFSteoOuOouP/KmV7dd9XTSdLgrBITlZZY/+BDh57+PsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78ee2b8ba4f16b928e933f3031707a99173415137ae8f5033d9434cfdb52c10","last_reissued_at":"2026-07-05T09:49:14.234372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:14.234372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Concept Models: Language Modeling in a Sentence Representation Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Mourachko, Artyom Kozhevnikov, Belen Alastruey, Christophe Ropers, David Dale, Eduardo S\\'anchez, Guillaume Couairon, Hady Elsahar, Holger Schwenk, Jo\\~ao Maria Janeiro, Kevin Heffernan, LCM team, Lo\\\"ic Barrault, Maha Elbayad, Mariano Coria, Marta R. Costa-juss\\`a, Paul-Ambroise Duquenne, Pierre Andrews, Robin San Roman, Safiyyah Saleem, Tuan Tran","submitted_at":"2024-12-11T23:36:20Z","abstract_excerpt":"LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, well beyond single words, to analyze information and to generate creative content. In this paper, we present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a concept. Concepts are language- and modality-agnostic and represent a highe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08821","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/2412.08821/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":"2412.08821","created_at":"2026-07-05T09:49:14.234435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08821v2","created_at":"2026-07-05T09:49:14.234435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08821","created_at":"2026-07-05T09:49:14.234435+00:00"},{"alias_kind":"pith_short_12","alias_value":"46HOFOF2J4LL","created_at":"2026-07-05T09:49:14.234435+00:00"},{"alias_kind":"pith_short_16","alias_value":"46HOFOF2J4LLSKHJ","created_at":"2026-07-05T09:49:14.234435+00:00"},{"alias_kind":"pith_short_8","alias_value":"46HOFOF2","created_at":"2026-07-05T09:49:14.234435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27378","citing_title":"Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25263","citing_title":"Mimir: Large-scale Multilingual Concept Modeling","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30196","citing_title":"Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2504.08528","citing_title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09630","citing_title":"Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06548","citing_title":"Continuous Latent Diffusion Language Model","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06285","citing_title":"LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06769","citing_title":"Training Large Language Models to Reason in a Continuous Latent Space","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG","json":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG.json","graph_json":"https://pith.science/api/pith-number/46HOFOF2J4LLSKHJGPZQGFYHVG/graph.json","events_json":"https://pith.science/api/pith-number/46HOFOF2J4LLSKHJGPZQGFYHVG/events.json","paper":"https://pith.science/paper/46HOFOF2"},"agent_actions":{"view_html":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG","download_json":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG.json","view_paper":"https://pith.science/paper/46HOFOF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08821&json=true","fetch_graph":"https://pith.science/api/pith-number/46HOFOF2J4LLSKHJGPZQGFYHVG/graph.json","fetch_events":"https://pith.science/api/pith-number/46HOFOF2J4LLSKHJGPZQGFYHVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG/action/storage_attestation","attest_author":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG/action/author_attestation","sign_citation":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG/action/citation_signature","submit_replication":"https://pith.science/pith/46HOFOF2J4LLSKHJGPZQGFYHVG/action/replication_record"}},"created_at":"2026-07-05T09:49:14.234435+00:00","updated_at":"2026-07-05T09:49:14.234435+00:00"}