{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WXKBZAMQ7KEOABVESDCRF3C277","short_pith_number":"pith:WXKBZAMQ","schema_version":"1.0","canonical_sha256":"b5d41c8190fa88e006a490c512ec5afff292d396db98cbbedff4be25f153102d","source":{"kind":"arxiv","id":"2606.05271","version":1},"attestation_state":"computed","paper":{"title":"BIDENT: Heterogeneous Operator-level Mapping for Efficient Edge Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Arghadip Das, Arnab Raha, Hoseok Kim, Soumendu Ghosh, Vijay Raghunathan","submitted_at":"2026-06-03T17:09:41Z","abstract_excerpt":"Modern edge System-on-Chips (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, yet current inference stacks map entire models to a single PU, leaving significant performance and energy efficiency on the table. This is exacerbated by emerging architectures such as state-space models (SSMs), Kolmogorov-Arnold networks (KANs), and multi-stage vision-language-action (VLA) pipelines, whose diverse operator characteristics are not uniformly suited to any single PU. We present BIDENT, a unified operator-level orchestration framework for heterogeneous edge inference th"},"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":"2606.05271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-03T17:09:41Z","cross_cats_sorted":[],"title_canon_sha256":"a0619d314d58cc76f322852ea64b113396bac2bc60992704cdd8a5a4c5267724","abstract_canon_sha256":"bc819b6e4517f8d814ce264c57229b2f82f4d3e5f6f83819004f81cad0083af7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:51.258271Z","signature_b64":"3aYa5x+i1bVuVe7yk/8qhMF7g/nEf/WIKiPBzK0mHlEDaqlQkZiIBBTAIL/XKQ++bq0VHOPn1d7dPTI4QCPaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d41c8190fa88e006a490c512ec5afff292d396db98cbbedff4be25f153102d","last_reissued_at":"2026-06-05T00:13:51.257849Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:51.257849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BIDENT: Heterogeneous Operator-level Mapping for Efficient Edge Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Arghadip Das, Arnab Raha, Hoseok Kim, Soumendu Ghosh, Vijay Raghunathan","submitted_at":"2026-06-03T17:09:41Z","abstract_excerpt":"Modern edge System-on-Chips (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, yet current inference stacks map entire models to a single PU, leaving significant performance and energy efficiency on the table. This is exacerbated by emerging architectures such as state-space models (SSMs), Kolmogorov-Arnold networks (KANs), and multi-stage vision-language-action (VLA) pipelines, whose diverse operator characteristics are not uniformly suited to any single PU. We present BIDENT, a unified operator-level orchestration framework for heterogeneous edge inference th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05271","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/2606.05271/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":"2606.05271","created_at":"2026-06-05T00:13:51.257911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05271v1","created_at":"2026-06-05T00:13:51.257911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05271","created_at":"2026-06-05T00:13:51.257911+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXKBZAMQ7KEO","created_at":"2026-06-05T00:13:51.257911+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXKBZAMQ7KEOABVE","created_at":"2026-06-05T00:13:51.257911+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXKBZAMQ","created_at":"2026-06-05T00:13:51.257911+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/WXKBZAMQ7KEOABVESDCRF3C277","json":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277.json","graph_json":"https://pith.science/api/pith-number/WXKBZAMQ7KEOABVESDCRF3C277/graph.json","events_json":"https://pith.science/api/pith-number/WXKBZAMQ7KEOABVESDCRF3C277/events.json","paper":"https://pith.science/paper/WXKBZAMQ"},"agent_actions":{"view_html":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277","download_json":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277.json","view_paper":"https://pith.science/paper/WXKBZAMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05271&json=true","fetch_graph":"https://pith.science/api/pith-number/WXKBZAMQ7KEOABVESDCRF3C277/graph.json","fetch_events":"https://pith.science/api/pith-number/WXKBZAMQ7KEOABVESDCRF3C277/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277/action/storage_attestation","attest_author":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277/action/author_attestation","sign_citation":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277/action/citation_signature","submit_replication":"https://pith.science/pith/WXKBZAMQ7KEOABVESDCRF3C277/action/replication_record"}},"created_at":"2026-06-05T00:13:51.257911+00:00","updated_at":"2026-06-05T00:13:51.257911+00:00"}