{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS","short_pith_number":"pith:EQ4SMJ6J","schema_version":"1.0","canonical_sha256":"24392627c9a5c4987b39a78b31a14b3c967bf2d3aa7d8d6bde44d78a699872c5","source":{"kind":"arxiv","id":"2605.31485","version":1},"attestation_state":"computed","paper":{"title":"Graphical einops: bridging tensor networks and computation graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["math.CT"],"primary_cat":"cs.LG","authors_text":"Nikhil Khatri, Vincent Wang-Ma\\'scianica","submitted_at":"2026-05-29T16:08:49Z","abstract_excerpt":"Architecture diagrams are ubiquitous in deep learning, but they are usually only representational: the tensor-program identities they suggest are still proved by prose and tensor-axis manipulation. We introduce a formal graphical calculus for the structural fragment of tensor programming underlying einops, making such diagrams proof-enabling. Our calculus represents tensor axes as nested graded tubes around a base type. The tube boundary recovers the undirected tensor-network view of axes, while the directed interior retains the operational reading of computation graphs. The key rewrite is gra"},"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":"2605.31485","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:08:49Z","cross_cats_sorted":["math.CT"],"title_canon_sha256":"83bb77e5219074cc50ecaff239f2b8a63447e34a1305ddae0c31906eca29c6c6","abstract_canon_sha256":"6dc8cb4720dc651aa1342e056828af5add76b32965ebbc5a48ed1b868921c720"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:08.559048Z","signature_b64":"SxTtjPZnXOTHp5DvQSTr2kHRBVwkjoFyojmUetfhrDlLlLm1eFKWIHy1UFRcmjjHrT+Xn7lwizg5THI9W5Y2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24392627c9a5c4987b39a78b31a14b3c967bf2d3aa7d8d6bde44d78a699872c5","last_reissued_at":"2026-06-01T02:04:08.558350Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:08.558350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graphical einops: bridging tensor networks and computation graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["math.CT"],"primary_cat":"cs.LG","authors_text":"Nikhil Khatri, Vincent Wang-Ma\\'scianica","submitted_at":"2026-05-29T16:08:49Z","abstract_excerpt":"Architecture diagrams are ubiquitous in deep learning, but they are usually only representational: the tensor-program identities they suggest are still proved by prose and tensor-axis manipulation. We introduce a formal graphical calculus for the structural fragment of tensor programming underlying einops, making such diagrams proof-enabling. Our calculus represents tensor axes as nested graded tubes around a base type. The tube boundary recovers the undirected tensor-network view of axes, while the directed interior retains the operational reading of computation graphs. The key rewrite is gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31485","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/2605.31485/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":"2605.31485","created_at":"2026-06-01T02:04:08.558479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31485v1","created_at":"2026-06-01T02:04:08.558479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31485","created_at":"2026-06-01T02:04:08.558479+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQ4SMJ6JUXCJ","created_at":"2026-06-01T02:04:08.558479+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQ4SMJ6JUXCJQ6ZZ","created_at":"2026-06-01T02:04:08.558479+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQ4SMJ6J","created_at":"2026-06-01T02:04:08.558479+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/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS","json":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS.json","graph_json":"https://pith.science/api/pith-number/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/graph.json","events_json":"https://pith.science/api/pith-number/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/events.json","paper":"https://pith.science/paper/EQ4SMJ6J"},"agent_actions":{"view_html":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS","download_json":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS.json","view_paper":"https://pith.science/paper/EQ4SMJ6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31485&json=true","fetch_graph":"https://pith.science/api/pith-number/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/graph.json","fetch_events":"https://pith.science/api/pith-number/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/action/storage_attestation","attest_author":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/action/author_attestation","sign_citation":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/action/citation_signature","submit_replication":"https://pith.science/pith/EQ4SMJ6JUXCJQ6ZZU6FTDIKLHS/action/replication_record"}},"created_at":"2026-06-01T02:04:08.558479+00:00","updated_at":"2026-06-01T02:04:08.558479+00:00"}