{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VM2TN7474AV3L6I6E3KQH43XJM","short_pith_number":"pith:VM2TN747","schema_version":"1.0","canonical_sha256":"ab3536ff9fe02bb5f91e26d503f3774b17bba67aaf18657d5e5cde74dc761358","source":{"kind":"arxiv","id":"2501.00712","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jason D. Lee, Jiajun Zhu, Pan Li, Peihao Wang, Ruisi Cai, Zhangyang Wang","submitted_at":"2025-01-01T03:23:00Z","abstract_excerpt":"Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce rigid patterns in attention maps, limiting the ability to model long-range dependencies and adapt to diverse tasks. Additionally, most positional encodings are learned as general biases, lacking the specialization required for different instances within a dataset. To address this, we propose con\\textbf{T}extualized equivari\\textbf{A}nt \\textbf{P}osition \\textb"},"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":"2501.00712","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T03:23:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7ba91fb430c5febca40c45f1c4b0fd187d3e880c8f6994b138ab2549e8aac9d","abstract_canon_sha256":"39ef4a3564bd2366cf9a67e7c4602d5129b8ff104c611982acd20bfe2d7a1451"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:52.046253Z","signature_b64":"NzjyvmqGTKLyYgW+/lRu+MVREs27AKqUqI0gzm4HpuL5mQrEFYsiwQuxweCdX0eW6JrrFb2RPazOqPyBKt8eBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab3536ff9fe02bb5f91e26d503f3774b17bba67aaf18657d5e5cde74dc761358","last_reissued_at":"2026-07-05T11:56:52.045764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:52.045764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jason D. Lee, Jiajun Zhu, Pan Li, Peihao Wang, Ruisi Cai, Zhangyang Wang","submitted_at":"2025-01-01T03:23:00Z","abstract_excerpt":"Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce rigid patterns in attention maps, limiting the ability to model long-range dependencies and adapt to diverse tasks. Additionally, most positional encodings are learned as general biases, lacking the specialization required for different instances within a dataset. To address this, we propose con\\textbf{T}extualized equivari\\textbf{A}nt \\textbf{P}osition \\textb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00712","kind":"arxiv","version":2},"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/2501.00712/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":"2501.00712","created_at":"2026-07-05T11:56:52.045825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00712v2","created_at":"2026-07-05T11:56:52.045825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00712","created_at":"2026-07-05T11:56:52.045825+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM2TN7474AV3","created_at":"2026-07-05T11:56:52.045825+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM2TN7474AV3L6I6","created_at":"2026-07-05T11:56:52.045825+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM2TN747","created_at":"2026-07-05T11:56:52.045825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21797","citing_title":"Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM","json":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM.json","graph_json":"https://pith.science/api/pith-number/VM2TN7474AV3L6I6E3KQH43XJM/graph.json","events_json":"https://pith.science/api/pith-number/VM2TN7474AV3L6I6E3KQH43XJM/events.json","paper":"https://pith.science/paper/VM2TN747"},"agent_actions":{"view_html":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM","download_json":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM.json","view_paper":"https://pith.science/paper/VM2TN747","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00712&json=true","fetch_graph":"https://pith.science/api/pith-number/VM2TN7474AV3L6I6E3KQH43XJM/graph.json","fetch_events":"https://pith.science/api/pith-number/VM2TN7474AV3L6I6E3KQH43XJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM/action/storage_attestation","attest_author":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM/action/author_attestation","sign_citation":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM/action/citation_signature","submit_replication":"https://pith.science/pith/VM2TN7474AV3L6I6E3KQH43XJM/action/replication_record"}},"created_at":"2026-07-05T11:56:52.045825+00:00","updated_at":"2026-07-05T11:56:52.045825+00:00"}