{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YLB74XUMF2OFEA5ECRRBSIBUXU","short_pith_number":"pith:YLB74XUM","schema_version":"1.0","canonical_sha256":"c2c3fe5e8c2e9c5203a41462192034bd109c75e2edb5ae2079df963fac591942","source":{"kind":"arxiv","id":"2506.03737","version":1},"attestation_state":"computed","paper":{"title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Guanghao Li, Haolong Qian, Hao Yu, Huaisong Zhang, Shannan Yan, Shuning Jia, Shunning Liu, Shuting Dong, Tangyu Jiang","submitted_at":"2025-06-04T09:10:02Z","abstract_excerpt":"The Transformer architecture has revolutionized various regions since it was proposed, and its effectiveness largely depends on the ability to encode positional information. Traditional position encoding methods exhibit significant limitations due to lack of robustness and flexibility of position. Therefore, Rotary Positional Encoding (RoPE) was proposed to alleviate these issues, which integrates positional information by rotating the embeddings in the attention mechanism. However, RoPE requires manually defined rotation matrices with limited transformation space, constraining the model's cap"},"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":"2506.03737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T09:10:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19ffe40f5e94b58a050aba8a5b201af48e64bef9f2e4a845dd6f8727030f68d3","abstract_canon_sha256":"b7283696461c650c4db90f4ab2810025d5225eaef34eeab52913a6d829f53f74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:50.999021Z","signature_b64":"r2AIqrligcGnyY83qWwekRPTwIG/3esn8FjIauu4k1xkqETQPobLWVK/rBF1fC6efNRPp1+DBWmRDvcBPf9zDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2c3fe5e8c2e9c5203a41462192034bd109c75e2edb5ae2079df963fac591942","last_reissued_at":"2026-07-05T11:15:50.998414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:50.998414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Guanghao Li, Haolong Qian, Hao Yu, Huaisong Zhang, Shannan Yan, Shuning Jia, Shunning Liu, Shuting Dong, Tangyu Jiang","submitted_at":"2025-06-04T09:10:02Z","abstract_excerpt":"The Transformer architecture has revolutionized various regions since it was proposed, and its effectiveness largely depends on the ability to encode positional information. Traditional position encoding methods exhibit significant limitations due to lack of robustness and flexibility of position. Therefore, Rotary Positional Encoding (RoPE) was proposed to alleviate these issues, which integrates positional information by rotating the embeddings in the attention mechanism. However, RoPE requires manually defined rotation matrices with limited transformation space, constraining the model's cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03737","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/2506.03737/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":"2506.03737","created_at":"2026-07-05T11:15:50.998502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03737v1","created_at":"2026-07-05T11:15:50.998502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03737","created_at":"2026-07-05T11:15:50.998502+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLB74XUMF2OF","created_at":"2026-07-05T11:15:50.998502+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLB74XUMF2OFEA5E","created_at":"2026-07-05T11:15:50.998502+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLB74XUM","created_at":"2026-07-05T11:15:50.998502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11007","citing_title":"The Transformer as a Polar State Estimator","ref_index":173,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU","json":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU.json","graph_json":"https://pith.science/api/pith-number/YLB74XUMF2OFEA5ECRRBSIBUXU/graph.json","events_json":"https://pith.science/api/pith-number/YLB74XUMF2OFEA5ECRRBSIBUXU/events.json","paper":"https://pith.science/paper/YLB74XUM"},"agent_actions":{"view_html":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU","download_json":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU.json","view_paper":"https://pith.science/paper/YLB74XUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03737&json=true","fetch_graph":"https://pith.science/api/pith-number/YLB74XUMF2OFEA5ECRRBSIBUXU/graph.json","fetch_events":"https://pith.science/api/pith-number/YLB74XUMF2OFEA5ECRRBSIBUXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU/action/storage_attestation","attest_author":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU/action/author_attestation","sign_citation":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU/action/citation_signature","submit_replication":"https://pith.science/pith/YLB74XUMF2OFEA5ECRRBSIBUXU/action/replication_record"}},"created_at":"2026-07-05T11:15:50.998502+00:00","updated_at":"2026-07-05T11:15:50.998502+00:00"}