{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DE5GCOGUKBX6ITV6RNIFSW55M3","short_pith_number":"pith:DE5GCOGU","canonical_record":{"source":{"id":"2605.14551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"10918c7d1531d7af828b935b62ad2066ec08e4c83dfa49c5a02751f0d5fbeb58","abstract_canon_sha256":"8379243c2969845b2c5bb1d5733afdaf32f9bb940ed85d639ba61553aa72bdb3"},"schema_version":"1.0"},"canonical_sha256":"193a6138d4506fe44ebe8b50595bbd66e3b1b84ae53a25f73a165089d99b315f","source":{"kind":"arxiv","id":"2605.14551","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14551","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14551v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14551","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"DE5GCOGUKBX6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DE5GCOGUKBX6ITV6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DE5GCOGU","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DE5GCOGUKBX6ITV6RNIFSW55M3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"10918c7d1531d7af828b935b62ad2066ec08e4c83dfa49c5a02751f0d5fbeb58","abstract_canon_sha256":"8379243c2969845b2c5bb1d5733afdaf32f9bb940ed85d639ba61553aa72bdb3"},"schema_version":"1.0"},"canonical_sha256":"193a6138d4506fe44ebe8b50595bbd66e3b1b84ae53a25f73a165089d99b315f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.707352Z","signature_b64":"Nj0iCcqmP0ZXHyNi/mKrEkRnEDB9IQufWv67SGNPeC5d3YzEI/Y34Lqr3w3GPslAmD4p0Iw5YHKlmfuz9qGqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"193a6138d4506fe44ebe8b50595bbd66e3b1b84ae53a25f73a165089d99b315f","last_reissued_at":"2026-05-17T23:39:05.706680Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.706680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14551","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WBdON02VIUgsCm5PCMzsFJTydOm0sex/H1xepJXGFMaWBV/cshIop1dChVijHHTAelw7eaySxxR8K2NZW4G9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:24:42.648978Z"},"content_sha256":"ef6a59b8e92f5280635bcab9c53bcbe2055b9e6ac114cd33eb8cc90df08f0820","schema_version":"1.0","event_id":"sha256:ef6a59b8e92f5280635bcab9c53bcbe2055b9e6ac114cd33eb8cc90df08f0820"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DE5GCOGUKBX6ITV6RNIFSW55M3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SeesawNet adaptively balances common and instance-specific dependencies in non-stationary time series forecasting.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hao Li, Liu Chong, Lu Zhang, Pengyang Wang, Yankai Chen, Yingjie Zhou","submitted_at":"2026-05-14T08:29:52Z","abstract_excerpt":"Instance normalization (IN) is widely used in non-stationary multivariate time series forecasting to reduce distribution shifts and highlight common patterns across samples. However, IN can over-smooth instance-specific structural information that is essential for modeling temporal and cross-channel heterogeneity. While prior methods further suppress distribution discrepancies or attempt to recover temporal specific dependencies, they often ignore a central tension: how to adaptively model common and instance-specific dependency based on each instance's non-stationary structures. To address th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SeesawNet consistently outperforms state-of-the-art methods on multiple real-world benchmarks by dynamically balancing common and instance-specific dependency modeling in both temporal and channel dimensions through ASNA.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the adaptive fusion of common dependencies from normalized sequences and specific dependencies from raw sequences, guided by instance-level non-stationarity, will reliably capture the required heterogeneity without introducing new smoothing artifacts or overfitting to training distribution shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SeesawNet adaptively balances common and instance-specific dependencies in non-stationary time series forecasting.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"82db9a855d29f880dbd7de53fe7c44a05c07ceb440bd909f82df7db89d6016e0"},"source":{"id":"2605.14551","kind":"arxiv","version":1},"verdict":{"id":"638e2cbb-2f53-4312-9cb8-f656306de9a7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:51:26.012761Z","strongest_claim":"SeesawNet consistently outperforms state-of-the-art methods on multiple real-world benchmarks by dynamically balancing common and instance-specific dependency modeling in both temporal and channel dimensions through ASNA.","one_line_summary":"SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the adaptive fusion of common dependencies from normalized sequences and specific dependencies from raw sequences, guided by instance-level non-stationarity, will reliably capture the required heterogeneity without introducing new smoothing artifacts or overfitting to training distribution shifts.","pith_extraction_headline":"SeesawNet adaptively balances common and instance-specific dependencies in non-stationary time series forecasting."},"references":{"count":21,"sample":[{"doi":"","year":2025,"title":"From dense to sparse: Event response for en- hanced residential load forecasting.IEEE Transactions on Instrumentation and Measurement,","work_id":"e8b8e84d-32a8-44c7-89d0-5a1c560330e5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Pathformer: Multi-scale trans- formers with adaptive pathways for time series forecast- ing.arXiv preprint arXiv:2402.05956,","work_id":"aa5120c5-17cc-4a68-b04d-100ae5de9bdd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Dish-ts: a general paradigm for alleviating distribution shift in time series forecasting","work_id":"4f385074-a836-4c03-b46b-e9e5915323e4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Deep frequency derivative learning for non-stationary time series forecasting.arXiv preprint arXiv:2407.00502,","work_id":"f7a3436c-016d-4647-8984-a3ff88bfa95d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Sin: Selective and interpretable normalization for long- term time series forecasting","work_id":"87b7b7bb-b192-4a69-a914-36daf83ab5df","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"f7f3d98b3ee73b30e60c83fc45ec0a4aca23cd3a05b7178671c18cde32b9451e","internal_anchors":2},"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":"638e2cbb-2f53-4312-9cb8-f656306de9a7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RKlBZ4LBron99IwFy5JwMBfjxf1AdtqxxL3UESdrPXe09Nz9nTSKiE8vY1Gl7xJhGSq1Nyhj0pcXxcwG8YyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:24:42.649524Z"},"content_sha256":"a83795141fa16af41ea66a08afcaedb36d262521b91ff1e24ab2d3b7c657f788","schema_version":"1.0","event_id":"sha256:a83795141fa16af41ea66a08afcaedb36d262521b91ff1e24ab2d3b7c657f788"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DE5GCOGUKBX6ITV6RNIFSW55M3/bundle.json","state_url":"https://pith.science/pith/DE5GCOGUKBX6ITV6RNIFSW55M3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DE5GCOGUKBX6ITV6RNIFSW55M3/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":"2026-06-02T20:24:42Z","links":{"resolver":"https://pith.science/pith/DE5GCOGUKBX6ITV6RNIFSW55M3","bundle":"https://pith.science/pith/DE5GCOGUKBX6ITV6RNIFSW55M3/bundle.json","state":"https://pith.science/pith/DE5GCOGUKBX6ITV6RNIFSW55M3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DE5GCOGUKBX6ITV6RNIFSW55M3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DE5GCOGUKBX6ITV6RNIFSW55M3","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":"8379243c2969845b2c5bb1d5733afdaf32f9bb940ed85d639ba61553aa72bdb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:29:52Z","title_canon_sha256":"10918c7d1531d7af828b935b62ad2066ec08e4c83dfa49c5a02751f0d5fbeb58"},"schema_version":"1.0","source":{"id":"2605.14551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14551","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14551v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14551","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"DE5GCOGUKBX6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DE5GCOGUKBX6ITV6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DE5GCOGU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:a83795141fa16af41ea66a08afcaedb36d262521b91ff1e24ab2d3b7c657f788","target":"graph","created_at":"2026-05-17T23:39:05Z","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":"SeesawNet consistently outperforms state-of-the-art methods on multiple real-world benchmarks by dynamically balancing common and instance-specific dependency modeling in both temporal and channel dimensions through ASNA."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the adaptive fusion of common dependencies from normalized sequences and specific dependencies from raw sequences, guided by instance-level non-stationarity, will reliably capture the required heterogeneity without introducing new smoothing artifacts or overfitting to training distribution shifts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SeesawNet adaptively balances common and instance-specific dependencies in non-stationary time series forecasting."}],"snapshot_sha256":"82db9a855d29f880dbd7de53fe7c44a05c07ceb440bd909f82df7db89d6016e0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Instance normalization (IN) is widely used in non-stationary multivariate time series forecasting to reduce distribution shifts and highlight common patterns across samples. However, IN can over-smooth instance-specific structural information that is essential for modeling temporal and cross-channel heterogeneity. While prior methods further suppress distribution discrepancies or attempt to recover temporal specific dependencies, they often ignore a central tension: how to adaptively model common and instance-specific dependency based on each instance's non-stationary structures. To address th","authors_text":"Hao Li, Liu Chong, Lu Zhang, Pengyang Wang, Yankai Chen, Yingjie Zhou","cross_cats":[],"headline":"SeesawNet adaptively balances common and instance-specific dependencies in non-stationary time series forecasting.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:29:52Z","title":"SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies"},"references":{"count":21,"internal_anchors":2,"resolved_work":21,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"From dense to sparse: Event response for en- hanced residential load forecasting.IEEE Transactions on Instrumentation and Measurement,","work_id":"e8b8e84d-32a8-44c7-89d0-5a1c560330e5","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Pathformer: Multi-scale trans- formers with adaptive pathways for time series forecast- ing.arXiv preprint arXiv:2402.05956,","work_id":"aa5120c5-17cc-4a68-b04d-100ae5de9bdd","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Dish-ts: a general paradigm for alleviating distribution shift in time series forecasting","work_id":"4f385074-a836-4c03-b46b-e9e5915323e4","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Deep frequency derivative learning for non-stationary time series forecasting.arXiv preprint arXiv:2407.00502,","work_id":"f7a3436c-016d-4647-8984-a3ff88bfa95d","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Sin: Selective and interpretable normalization for long- term time series forecasting","work_id":"87b7b7bb-b192-4a69-a914-36daf83ab5df","year":2024}],"snapshot_sha256":"f7f3d98b3ee73b30e60c83fc45ec0a4aca23cd3a05b7178671c18cde32b9451e"},"source":{"id":"2605.14551","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:51:26.012761Z","id":"638e2cbb-2f53-4312-9cb8-f656306de9a7","model_set":{"reader":"grok-4.3"},"one_line_summary":"SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SeesawNet adaptively balances common and instance-specific dependencies in non-stationary time series forecasting.","strongest_claim":"SeesawNet consistently outperforms state-of-the-art methods on multiple real-world benchmarks by dynamically balancing common and instance-specific dependency modeling in both temporal and channel dimensions through ASNA.","weakest_assumption":"That the adaptive fusion of common dependencies from normalized sequences and specific dependencies from raw sequences, guided by instance-level non-stationarity, will reliably capture the required heterogeneity without introducing new smoothing artifacts or overfitting to training distribution shifts."}},"verdict_id":"638e2cbb-2f53-4312-9cb8-f656306de9a7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ef6a59b8e92f5280635bcab9c53bcbe2055b9e6ac114cd33eb8cc90df08f0820","target":"record","created_at":"2026-05-17T23:39:05Z","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":"8379243c2969845b2c5bb1d5733afdaf32f9bb940ed85d639ba61553aa72bdb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:29:52Z","title_canon_sha256":"10918c7d1531d7af828b935b62ad2066ec08e4c83dfa49c5a02751f0d5fbeb58"},"schema_version":"1.0","source":{"id":"2605.14551","kind":"arxiv","version":1}},"canonical_sha256":"193a6138d4506fe44ebe8b50595bbd66e3b1b84ae53a25f73a165089d99b315f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"193a6138d4506fe44ebe8b50595bbd66e3b1b84ae53a25f73a165089d99b315f","first_computed_at":"2026-05-17T23:39:05.706680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:05.706680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nj0iCcqmP0ZXHyNi/mKrEkRnEDB9IQufWv67SGNPeC5d3YzEI/Y34Lqr3w3GPslAmD4p0Iw5YHKlmfuz9qGqAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:05.707352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef6a59b8e92f5280635bcab9c53bcbe2055b9e6ac114cd33eb8cc90df08f0820","sha256:a83795141fa16af41ea66a08afcaedb36d262521b91ff1e24ab2d3b7c657f788"],"state_sha256":"7ae0c0bdafb00e0081d786d7a02c18d1366c9273f5beb7ea6b52e537f119c964"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KvVubH6eWbhC0Ngg314jI36slQYuvTodBk6wOmEB5kO68OAaF47siylx8EBWOnoooSow4jtxCNUzn67aubZlAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:24:42.652207Z","bundle_sha256":"9dcf18533a5204d4b15b6731643cfda658bf0cfc1451e10ab4b25e17a1090052"}}