{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3DJTS3CUCYCOVM2XLJSF7B3VJ3","short_pith_number":"pith:3DJTS3CU","schema_version":"1.0","canonical_sha256":"d8d3396c541604eab3575a645f87754efbfa599e9c6cd3a9087b640d5f120e38","source":{"kind":"arxiv","id":"2305.13362","version":1},"attestation_state":"computed","paper":{"title":"On quantum backpropagation, information reuse, and cheating measurement collapse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Amira Abbas, Dar Gilboa, Hsin-Yuan Huang, Jarrod R. McClean, Ramis Movassagh, Robbie King, William J. Huggins","submitted_at":"2023-05-22T18:00:02Z","abstract_excerpt":"The success of modern deep learning hinges on the ability to train neural networks at scale. Through clever reuse of intermediate information, backpropagation facilitates training through gradient computation at a total cost roughly proportional to running the function, rather than incurring an additional factor proportional to the number of parameters - which can now be in the trillions. Naively, one expects that quantum measurement collapse entirely rules out the reuse of quantum information as in backpropagation. But recent developments in shadow tomography, which assumes access to multiple"},"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":"2305.13362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2023-05-22T18:00:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0619c43a8b62122addc69543c2e1e622a9d4ef9063c96cbd4c52029c49b3da92","abstract_canon_sha256":"6a95934c9b2021e7f2d65e2c25401f7dff474ccd693c4caf2050c4b9f14268ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:30.452476Z","signature_b64":"rwzVFEg3llpgKQhe/bboOtU1UcOqwc1FUgn0bv6O596G9BTymXpf1Sn1nLRsO0nxcfnndRdEexOOR3w0gKBPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8d3396c541604eab3575a645f87754efbfa599e9c6cd3a9087b640d5f120e38","last_reissued_at":"2026-07-05T07:54:30.451956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:30.451956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On quantum backpropagation, information reuse, and cheating measurement collapse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Amira Abbas, Dar Gilboa, Hsin-Yuan Huang, Jarrod R. McClean, Ramis Movassagh, Robbie King, William J. Huggins","submitted_at":"2023-05-22T18:00:02Z","abstract_excerpt":"The success of modern deep learning hinges on the ability to train neural networks at scale. Through clever reuse of intermediate information, backpropagation facilitates training through gradient computation at a total cost roughly proportional to running the function, rather than incurring an additional factor proportional to the number of parameters - which can now be in the trillions. Naively, one expects that quantum measurement collapse entirely rules out the reuse of quantum information as in backpropagation. But recent developments in shadow tomography, which assumes access to multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13362","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/2305.13362/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":"2305.13362","created_at":"2026-07-05T07:54:30.452019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13362v1","created_at":"2026-07-05T07:54:30.452019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13362","created_at":"2026-07-05T07:54:30.452019+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DJTS3CUCYCO","created_at":"2026-07-05T07:54:30.452019+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DJTS3CUCYCOVM2X","created_at":"2026-07-05T07:54:30.452019+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DJTS3CU","created_at":"2026-07-05T07:54:30.452019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09734","citing_title":"Adaptive directional gradients for parameterised quantum circuits","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2306.02620","citing_title":"Feasibility of performing quantum chemistry calculations on quantum computers","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10577","citing_title":"Training continuously-coupled reconfigurable photonic chips with quantum machine learning","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3","json":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3.json","graph_json":"https://pith.science/api/pith-number/3DJTS3CUCYCOVM2XLJSF7B3VJ3/graph.json","events_json":"https://pith.science/api/pith-number/3DJTS3CUCYCOVM2XLJSF7B3VJ3/events.json","paper":"https://pith.science/paper/3DJTS3CU"},"agent_actions":{"view_html":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3","download_json":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3.json","view_paper":"https://pith.science/paper/3DJTS3CU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13362&json=true","fetch_graph":"https://pith.science/api/pith-number/3DJTS3CUCYCOVM2XLJSF7B3VJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/3DJTS3CUCYCOVM2XLJSF7B3VJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3/action/storage_attestation","attest_author":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3/action/author_attestation","sign_citation":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3/action/citation_signature","submit_replication":"https://pith.science/pith/3DJTS3CUCYCOVM2XLJSF7B3VJ3/action/replication_record"}},"created_at":"2026-07-05T07:54:30.452019+00:00","updated_at":"2026-07-05T07:54:30.452019+00:00"}