{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7PKFZUJ3XB2DJYOKSQJYAOEOU","short_pith_number":"pith:L7PKFZUJ","schema_version":"1.0","canonical_sha256":"5fdea2e689ddc3a1a70e54a09c01c47533871cefdb9f75c2ce017d4ff9d69206","source":{"kind":"arxiv","id":"2606.12688","version":1},"attestation_state":"computed","paper":{"title":"M*: A Modular, Extensible, Serving System for Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Atindra Jha, Baris Kasikci, Irmak Sivgin, Jure Leskovec, Keisuke Kamahori, Luke Zettlemoyer, Mark Horowitz, Naomi Sagan, Olivia Hsu, Rohan Sanda, Stephanie Wang, Steven Gao","submitted_at":"2026-06-10T21:22:22Z","abstract_excerpt":"We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors. Such architectures underpin a broad class of multimodal models, including unified multimodal models, omni models, speech-language models, vision-language-action policies, and world models. However, existing model serving frameworks were built on narrow assumptions about model structure, making them ill-suited to accommodate this new architectural diversity. Here we present"},"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":"2606.12688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T21:22:22Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"12529b2695f425b95a747c2e385c0997ad6b74fe20255a0bde26ea7fae752f8d","abstract_canon_sha256":"7fc97d3cf8defb032b74fff8512488142566b8d35748d9a4cd8ee926a01f486f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:45.544677Z","signature_b64":"ml0zSoJdJUUJU9nX3nci2bRkKQO53LOAIaHS1m6KGz+eRZznyGLi6T0xiGyuAS9i9/d3PCWBZy6fx7afQipwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fdea2e689ddc3a1a70e54a09c01c47533871cefdb9f75c2ce017d4ff9d69206","last_reissued_at":"2026-06-12T01:08:45.543849Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:45.543849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M*: A Modular, Extensible, Serving System for Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Atindra Jha, Baris Kasikci, Irmak Sivgin, Jure Leskovec, Keisuke Kamahori, Luke Zettlemoyer, Mark Horowitz, Naomi Sagan, Olivia Hsu, Rohan Sanda, Stephanie Wang, Steven Gao","submitted_at":"2026-06-10T21:22:22Z","abstract_excerpt":"We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors. Such architectures underpin a broad class of multimodal models, including unified multimodal models, omni models, speech-language models, vision-language-action policies, and world models. However, existing model serving frameworks were built on narrow assumptions about model structure, making them ill-suited to accommodate this new architectural diversity. Here we present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12688","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/2606.12688/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":"2606.12688","created_at":"2026-06-12T01:08:45.543984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12688v1","created_at":"2026-06-12T01:08:45.543984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12688","created_at":"2026-06-12T01:08:45.543984+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7PKFZUJ3XB2","created_at":"2026-06-12T01:08:45.543984+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7PKFZUJ3XB2DJYO","created_at":"2026-06-12T01:08:45.543984+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7PKFZUJ","created_at":"2026-06-12T01:08:45.543984+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/L7PKFZUJ3XB2DJYOKSQJYAOEOU","json":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU.json","graph_json":"https://pith.science/api/pith-number/L7PKFZUJ3XB2DJYOKSQJYAOEOU/graph.json","events_json":"https://pith.science/api/pith-number/L7PKFZUJ3XB2DJYOKSQJYAOEOU/events.json","paper":"https://pith.science/paper/L7PKFZUJ"},"agent_actions":{"view_html":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU","download_json":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU.json","view_paper":"https://pith.science/paper/L7PKFZUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12688&json=true","fetch_graph":"https://pith.science/api/pith-number/L7PKFZUJ3XB2DJYOKSQJYAOEOU/graph.json","fetch_events":"https://pith.science/api/pith-number/L7PKFZUJ3XB2DJYOKSQJYAOEOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU/action/storage_attestation","attest_author":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU/action/author_attestation","sign_citation":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU/action/citation_signature","submit_replication":"https://pith.science/pith/L7PKFZUJ3XB2DJYOKSQJYAOEOU/action/replication_record"}},"created_at":"2026-06-12T01:08:45.543984+00:00","updated_at":"2026-06-12T01:08:45.543984+00:00"}