{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L4YM7N2AQEE2RLX53XPS2Z6F7B","short_pith_number":"pith:L4YM7N2A","canonical_record":{"source":{"id":"2504.05336","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-04-05T02:52:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31e5a7a4b86a4cf5e0fd886cae0c0432eb18339134daeb420886b7aab8347a31","abstract_canon_sha256":"6ff549ffd089093d8dc929fd8add3f583e5d20f8e708ce70d3ca676c9650d6ce"},"schema_version":"1.0"},"canonical_sha256":"5f30cfb7408109a8aefddddf2d67c5f860f6d44e03a24c0b07a956c5785e95e0","source":{"kind":"arxiv","id":"2504.05336","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05336","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05336v4","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05336","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"L4YM7N2AQEE2","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"L4YM7N2AQEE2RLX5","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"L4YM7N2A","created_at":"2026-06-24T01:14:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L4YM7N2AQEE2RLX53XPS2Z6F7B","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05336","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-04-05T02:52:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31e5a7a4b86a4cf5e0fd886cae0c0432eb18339134daeb420886b7aab8347a31","abstract_canon_sha256":"6ff549ffd089093d8dc929fd8add3f583e5d20f8e708ce70d3ca676c9650d6ce"},"schema_version":"1.0"},"canonical_sha256":"5f30cfb7408109a8aefddddf2d67c5f860f6d44e03a24c0b07a956c5785e95e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:20.043885Z","signature_b64":"Lu7BEGA3/VYIKN6+lzbBUafF0/M1QNeD6n2W7LyGildFRDcSjaV07bdQcfUrjnLP/RIWq/hB45wiUjk3MEdZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f30cfb7408109a8aefddddf2d67c5f860f6d44e03a24c0b07a956c5785e95e0","last_reissued_at":"2026-06-24T01:14:20.043417Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:20.043417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05336","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ThLoCg6JftQU0uiUJn0iKfX3G86VfwyyzJEGriZT2Tozu9xyWiAyv1xlVrLpMY/ba0SzQ8yFR6ibywiznteBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:18:11.824575Z"},"content_sha256":"5857747a00fde86b61d7ab8ce6298c60679d37f65bd1d8f67678751b133f7114","schema_version":"1.0","event_id":"sha256:5857747a00fde86b61d7ab8ce6298c60679d37f65bd1d8f67678751b133f7114"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L4YM7N2AQEE2RLX53XPS2Z6F7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantum Adaptive Self-Attention for Quantum Transformer Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A Transformer with one 36-parameter quantum circuit in the value projection of a single encoder layer achieves best results on chaotic time-series tasks.","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Chi-Sheng Chen, En-Jui Kuo","submitted_at":"2025-04-05T02:52:37Z","abstract_excerpt":"A recurring weakness in quantum machine learning (QML) is that reported ``quantum advantages'' are seldom tested against a \\emph{capacity-matched} classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly -- a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does \\emph{not} help, and validation on real quantum hardware -- which we develop and apply through a concret"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A hybrid Transformer that replaces the value projection in a single encoder layer with a parameterized quantum circuit using only 36 trainable quantum parameters achieves the best MSE on 4 of 9 synthetic benchmarks and a 6.0% MAE reduction on the ETTh1 dataset, with quantum benefit being task-conditional and position mattering more than quantum layer count.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The observed performance differences are caused by the quantum circuit itself rather than by classical hyperparameter choices, random seeds, or post-hoc selection of which tasks count as 'chaotic' versus 'periodic'; the ablation study and statistical comparisons (p=0.009) fully isolate the quantum contribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"QASA with one 36-parameter quantum layer in a Transformer achieves best MSE on 4 of 9 synthetic tasks and 6% MAE reduction on ETTh1, outperforming larger quantum models on chaotic/noisy signals while classical models win on clean periodic data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A Transformer with one 36-parameter quantum circuit in the value projection of a single encoder layer achieves best results on chaotic time-series tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cd5a23a8b0002b4dc086f44c48866149f4cc1b522171c21cac79d87e2254274c"},"source":{"id":"2504.05336","kind":"arxiv","version":4},"verdict":{"id":"1e8fe4b7-b3cf-49e6-b873-9b58dade6c86","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-22T21:38:40.317818Z","strongest_claim":"A hybrid Transformer that replaces the value projection in a single encoder layer with a parameterized quantum circuit using only 36 trainable quantum parameters achieves the best MSE on 4 of 9 synthetic benchmarks and a 6.0% MAE reduction on the ETTh1 dataset, with quantum benefit being task-conditional and position mattering more than quantum layer count.","one_line_summary":"QASA with one 36-parameter quantum layer in a Transformer achieves best MSE on 4 of 9 synthetic tasks and 6% MAE reduction on ETTh1, outperforming larger quantum models on chaotic/noisy signals while classical models win on clean periodic data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The observed performance differences are caused by the quantum circuit itself rather than by classical hyperparameter choices, random seeds, or post-hoc selection of which tasks count as 'chaotic' versus 'periodic'; the ablation study and statistical comparisons (p=0.009) fully isolate the quantum contribution.","pith_extraction_headline":"A Transformer with one 36-parameter quantum circuit in the value projection of a single encoder layer achieves best results on chaotic time-series tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.05336/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"},"verdict_id":"1e8fe4b7-b3cf-49e6-b873-9b58dade6c86"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M1u/nnafvNWY1KGkOD43QQY414NJR+cFYZtnf05jpSibGnb9x5qp2dEC95KY/RtTG1qyKrAh6Pkxb9q3yCN8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:18:11.825318Z"},"content_sha256":"a290b3894f31e8564dcd84dcd68a09e1e802856431634eb67c293ec4947dfaf4","schema_version":"1.0","event_id":"sha256:a290b3894f31e8564dcd84dcd68a09e1e802856431634eb67c293ec4947dfaf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B/bundle.json","state_url":"https://pith.science/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T06:18:11Z","links":{"resolver":"https://pith.science/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B","bundle":"https://pith.science/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B/bundle.json","state":"https://pith.science/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4YM7N2AQEE2RLX53XPS2Z6F7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L4YM7N2AQEE2RLX53XPS2Z6F7B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6ff549ffd089093d8dc929fd8add3f583e5d20f8e708ce70d3ca676c9650d6ce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-04-05T02:52:37Z","title_canon_sha256":"31e5a7a4b86a4cf5e0fd886cae0c0432eb18339134daeb420886b7aab8347a31"},"schema_version":"1.0","source":{"id":"2504.05336","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05336","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05336v4","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05336","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"L4YM7N2AQEE2","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"L4YM7N2AQEE2RLX5","created_at":"2026-06-24T01:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"L4YM7N2A","created_at":"2026-06-24T01:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:a290b3894f31e8564dcd84dcd68a09e1e802856431634eb67c293ec4947dfaf4","target":"graph","created_at":"2026-06-24T01:14:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"A hybrid Transformer that replaces the value projection in a single encoder layer with a parameterized quantum circuit using only 36 trainable quantum parameters achieves the best MSE on 4 of 9 synthetic benchmarks and a 6.0% MAE reduction on the ETTh1 dataset, with quantum benefit being task-conditional and position mattering more than quantum layer count."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The observed performance differences are caused by the quantum circuit itself rather than by classical hyperparameter choices, random seeds, or post-hoc selection of which tasks count as 'chaotic' versus 'periodic'; the ablation study and statistical comparisons (p=0.009) fully isolate the quantum contribution."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"QASA with one 36-parameter quantum layer in a Transformer achieves best MSE on 4 of 9 synthetic tasks and 6% MAE reduction on ETTh1, outperforming larger quantum models on chaotic/noisy signals while classical models win on clean periodic data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A Transformer with one 36-parameter quantum circuit in the value projection of a single encoder layer achieves best results on chaotic time-series tasks."}],"snapshot_sha256":"cd5a23a8b0002b4dc086f44c48866149f4cc1b522171c21cac79d87e2254274c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.05336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recurring weakness in quantum machine learning (QML) is that reported ``quantum advantages'' are seldom tested against a \\emph{capacity-matched} classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly -- a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does \\emph{not} help, and validation on real quantum hardware -- which we develop and apply through a concret","authors_text":"Chi-Sheng Chen, En-Jui Kuo","cross_cats":["cs.LG"],"headline":"A Transformer with one 36-parameter quantum circuit in the value projection of a single encoder layer achieves best results on chaotic time-series tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-04-05T02:52:37Z","title":"Quantum Adaptive Self-Attention for Quantum Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05336","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-22T21:38:40.317818Z","id":"1e8fe4b7-b3cf-49e6-b873-9b58dade6c86","model_set":{"reader":"grok-4.3"},"one_line_summary":"QASA with one 36-parameter quantum layer in a Transformer achieves best MSE on 4 of 9 synthetic tasks and 6% MAE reduction on ETTh1, outperforming larger quantum models on chaotic/noisy signals while classical models win on clean periodic data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A Transformer with one 36-parameter quantum circuit in the value projection of a single encoder layer achieves best results on chaotic time-series tasks.","strongest_claim":"A hybrid Transformer that replaces the value projection in a single encoder layer with a parameterized quantum circuit using only 36 trainable quantum parameters achieves the best MSE on 4 of 9 synthetic benchmarks and a 6.0% MAE reduction on the ETTh1 dataset, with quantum benefit being task-conditional and position mattering more than quantum layer count.","weakest_assumption":"The observed performance differences are caused by the quantum circuit itself rather than by classical hyperparameter choices, random seeds, or post-hoc selection of which tasks count as 'chaotic' versus 'periodic'; the ablation study and statistical comparisons (p=0.009) fully isolate the quantum contribution."}},"verdict_id":"1e8fe4b7-b3cf-49e6-b873-9b58dade6c86"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5857747a00fde86b61d7ab8ce6298c60679d37f65bd1d8f67678751b133f7114","target":"record","created_at":"2026-06-24T01:14:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6ff549ffd089093d8dc929fd8add3f583e5d20f8e708ce70d3ca676c9650d6ce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-04-05T02:52:37Z","title_canon_sha256":"31e5a7a4b86a4cf5e0fd886cae0c0432eb18339134daeb420886b7aab8347a31"},"schema_version":"1.0","source":{"id":"2504.05336","kind":"arxiv","version":4}},"canonical_sha256":"5f30cfb7408109a8aefddddf2d67c5f860f6d44e03a24c0b07a956c5785e95e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f30cfb7408109a8aefddddf2d67c5f860f6d44e03a24c0b07a956c5785e95e0","first_computed_at":"2026-06-24T01:14:20.043417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:20.043417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lu7BEGA3/VYIKN6+lzbBUafF0/M1QNeD6n2W7LyGildFRDcSjaV07bdQcfUrjnLP/RIWq/hB45wiUjk3MEdZCg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:20.043885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05336","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5857747a00fde86b61d7ab8ce6298c60679d37f65bd1d8f67678751b133f7114","sha256:a290b3894f31e8564dcd84dcd68a09e1e802856431634eb67c293ec4947dfaf4"],"state_sha256":"dcda10696e913f7bd1bc012f37ccbfe47124ce675c6ca3b4291c9b64cd02c321"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xeAxI0xWcxpNh0emq4zieRZPVxuoVpEWKDyZqs8V0UAaIlGQ2O6OboAZ+6/NQaSMo5MOxeBqa3epgFmMnmbGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:18:11.831359Z","bundle_sha256":"65bf945960f5ec981870f464bd733c2667a3c1b6c3bc681986f7f27917570f74"}}