{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBJL6W7Q76IK2TRGQCS7KLZRPV","short_pith_number":"pith:MBJL6W7Q","schema_version":"1.0","canonical_sha256":"6052bf5bf0ff90ad4e2680a5f52f317d66dd3c0f102777897dc6ca5f29f25296","source":{"kind":"arxiv","id":"2505.03281","version":1},"attestation_state":"computed","paper":{"title":"Physics-inspired Energy Transition Neural Network for Sequence Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baile Xu, Furao Shen, Jian Zhao, Junyi An, Zhou Wu","submitted_at":"2025-05-06T08:07:15Z","abstract_excerpt":"Recently, the superior performance of Transformers has made them a more robust and scalable solution for sequence modeling than traditional recurrent neural networks (RNNs). However, the effectiveness of Transformer in capturing long-term dependencies is primarily attributed to their comprehensive pair-modeling process rather than inherent inductive biases toward sequence semantics. In this study, we explore the capabilities of pure RNNs and reassess their long-term learning mechanisms. Inspired by the physics energy transition models that track energy changes over time, we propose a effective"},"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":"2505.03281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T08:07:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"656759992b3bf85bd4893adc81fe4b3cc36c9c587f8ceae7a74bcf14d903f79b","abstract_canon_sha256":"28b2b8f3424e8e92b6c3a41baa5497c5f00d713333c2bed3977b531e5f06e1d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:13.320746Z","signature_b64":"EW2vArs26OKgEIstL1fWZLkCUvq1fEuAbAbXXMcp+ixR028bkw+flEvBGoB2E+9plOeKpKRRm2e4OfZo55PIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6052bf5bf0ff90ad4e2680a5f52f317d66dd3c0f102777897dc6ca5f29f25296","last_reissued_at":"2026-07-05T10:59:13.320330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:13.320330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics-inspired Energy Transition Neural Network for Sequence Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baile Xu, Furao Shen, Jian Zhao, Junyi An, Zhou Wu","submitted_at":"2025-05-06T08:07:15Z","abstract_excerpt":"Recently, the superior performance of Transformers has made them a more robust and scalable solution for sequence modeling than traditional recurrent neural networks (RNNs). However, the effectiveness of Transformer in capturing long-term dependencies is primarily attributed to their comprehensive pair-modeling process rather than inherent inductive biases toward sequence semantics. In this study, we explore the capabilities of pure RNNs and reassess their long-term learning mechanisms. Inspired by the physics energy transition models that track energy changes over time, we propose a effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03281","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/2505.03281/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":"2505.03281","created_at":"2026-07-05T10:59:13.320388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03281v1","created_at":"2026-07-05T10:59:13.320388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03281","created_at":"2026-07-05T10:59:13.320388+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBJL6W7Q76IK","created_at":"2026-07-05T10:59:13.320388+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBJL6W7Q76IK2TRG","created_at":"2026-07-05T10:59:13.320388+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBJL6W7Q","created_at":"2026-07-05T10:59:13.320388+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/MBJL6W7Q76IK2TRGQCS7KLZRPV","json":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV.json","graph_json":"https://pith.science/api/pith-number/MBJL6W7Q76IK2TRGQCS7KLZRPV/graph.json","events_json":"https://pith.science/api/pith-number/MBJL6W7Q76IK2TRGQCS7KLZRPV/events.json","paper":"https://pith.science/paper/MBJL6W7Q"},"agent_actions":{"view_html":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV","download_json":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV.json","view_paper":"https://pith.science/paper/MBJL6W7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03281&json=true","fetch_graph":"https://pith.science/api/pith-number/MBJL6W7Q76IK2TRGQCS7KLZRPV/graph.json","fetch_events":"https://pith.science/api/pith-number/MBJL6W7Q76IK2TRGQCS7KLZRPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV/action/storage_attestation","attest_author":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV/action/author_attestation","sign_citation":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV/action/citation_signature","submit_replication":"https://pith.science/pith/MBJL6W7Q76IK2TRGQCS7KLZRPV/action/replication_record"}},"created_at":"2026-07-05T10:59:13.320388+00:00","updated_at":"2026-07-05T10:59:13.320388+00:00"}