{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P6HWEOIAITREBDGKJM4THPONVZ","short_pith_number":"pith:P6HWEOIA","canonical_record":{"source":{"id":"2605.12709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T20:16:48Z","cross_cats_sorted":[],"title_canon_sha256":"a8967f33e4b96de2001bd2bd95c4e47771ccab470fdcff1079d9769fac1a1c5d","abstract_canon_sha256":"84832a61feb1ae43c1b21db4171f72bf6512e37535219643a767cb11eeb33c96"},"schema_version":"1.0"},"canonical_sha256":"7f8f62390044e2408cca4b3933bdcdae4a61dbd3612e16d1269a3b9ea27e2a83","source":{"kind":"arxiv","id":"2605.12709","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12709","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12709v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12709","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"P6HWEOIAITRE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"P6HWEOIAITREBDGK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"P6HWEOIA","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P6HWEOIAITREBDGKJM4THPONVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T20:16:48Z","cross_cats_sorted":[],"title_canon_sha256":"a8967f33e4b96de2001bd2bd95c4e47771ccab470fdcff1079d9769fac1a1c5d","abstract_canon_sha256":"84832a61feb1ae43c1b21db4171f72bf6512e37535219643a767cb11eeb33c96"},"schema_version":"1.0"},"canonical_sha256":"7f8f62390044e2408cca4b3933bdcdae4a61dbd3612e16d1269a3b9ea27e2a83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:49.572928Z","signature_b64":"b/XJEHTxWqkUFK8GdI/NKsPUhXCiEcwJSkcvkhJq4HwKzzFNd2ABj00t6wHbHmrmQjNWJy5iwwkW4bLRjO5iBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f8f62390044e2408cca4b3933bdcdae4a61dbd3612e16d1269a3b9ea27e2a83","last_reissued_at":"2026-05-18T03:09:49.571962Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:49.571962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12709","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":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XD3sZiizti/abG8izqA/nas+bPblGHyrRlsjB42td0DUjDoijyNFeD0OSGociAmB4MsSqF8sImXD5vbwUGccAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:31:25.847377Z"},"content_sha256":"e99e0011040bcf6eb1923d33e728a20bae3395e2fecfc8a845e781b96a9946dc","schema_version":"1.0","event_id":"sha256:e99e0011040bcf6eb1923d33e728a20bae3395e2fecfc8a845e781b96a9946dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P6HWEOIAITREBDGKJM4THPONVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Spectral Energy Centroid computed from a target signal selects embedding frequencies that improve implicit neural representation performance regardless of model depth.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Kania, Maciej Rut, Przemys{\\l}aw Spurek, Tomasz D\\k{a}dela","submitted_at":"2026-05-12T20:16:48Z","abstract_excerpt":"Implicit Neural Representations (INRs) model continuous signals using multilayer perceptrons (MLPs), enabling compact, differentiable, and high-fidelity representations of data across diverse domains. However, due to the low-frequency bias of MLPs that prevents effective learning of small details, the model's frequency must be carefully tuned through the embedding layer. Prior work established that this tuning can be performed before training based on the target signal, but it did not account for the significant effect of model depth, indicating that our understanding of the relationship betwe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that SEC is a versatile tool for INR analysis, demonstrating its utility across three tasks: (1) a data-driven strategy (SEC-Conf) for hyperparameter selection that outperforms existing heuristics and is robust to model depth, (2) a reliable proxy for signal complexity, and (3) effective alignment of spectral biases across diverse INR architectures.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Spectral Energy Centroid computed from the target signal accurately predicts the optimal embedding frequency for an INR of arbitrary depth and architecture without requiring any training-time feedback.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Spectral Energy Centroid is a new metric that quantifies signal frequency and INR spectral bias, supporting better hyperparameter selection and cross-architecture analysis.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Spectral Energy Centroid computed from a target signal selects embedding frequencies that improve implicit neural representation performance regardless of model depth.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"228c48eaf4e307292b472a6c0ff09739a2956912a01e41735496957ceca6d883"},"source":{"id":"2605.12709","kind":"arxiv","version":1},"verdict":{"id":"e97b4ed4-a29c-4be9-8027-c5baef2eda3e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:32:37.587626Z","strongest_claim":"We show that SEC is a versatile tool for INR analysis, demonstrating its utility across three tasks: (1) a data-driven strategy (SEC-Conf) for hyperparameter selection that outperforms existing heuristics and is robust to model depth, (2) a reliable proxy for signal complexity, and (3) effective alignment of spectral biases across diverse INR architectures.","one_line_summary":"Spectral Energy Centroid is a new metric that quantifies signal frequency and INR spectral bias, supporting better hyperparameter selection and cross-architecture analysis.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Spectral Energy Centroid computed from the target signal accurately predicts the optimal embedding frequency for an INR of arbitrary depth and architecture without requiring any training-time feedback.","pith_extraction_headline":"Spectral Energy Centroid computed from a target signal selects embedding frequencies that improve implicit neural representation performance regardless of model depth."},"references":{"count":23,"sample":[{"doi":"","year":2025,"title":"Shenoy, and Steven H","work_id":"c3d81a28-946c-40e8-ab28-538954bb24c3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A scalable Walsh-Hadamard regularizer to overcome the low-degree spectral bias of neural networks","work_id":"8948c3e9-9df3-4376-a1c5-099df3205a38","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Fresh: Frequency shifting for accelerated neural representation learning","work_id":"aba29de8-0807-411f-bed3-ce95987f12bb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","ref_index":4,"cited_arxiv_id":"1412.6980","is_internal_anchor":true},{"doi":"","year":2020,"title":"J. Liu, D. Liu, W. Yang, S. Xia, X. Zhang, and Y . Dai. A comprehensive benchmark for single image compression artifact reduction.IEEE Transactions on Image Processing, 29:7845–7860, 2020","work_id":"6e891e92-e2ed-4ca1-bfea-7ef100f9d31b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"edf307ec8131a91f82851a219d9e45c39df5a3b64f6c628dfa1db929245820a2","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0f430d9e1edd481e2ecbba9f2d6fb0a5cc32de2b851bc3a329534569316de71d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e97b4ed4-a29c-4be9-8027-c5baef2eda3e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ypPDyBC+sf6klWOkcrN+XX35PpAvI0qHtECEGV9xRo8/xz2gUBFm6udW3x82KYJOXZJX75eznhr9Ax7HyDkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:31:25.848032Z"},"content_sha256":"e58a1c3e316a3fe1c0d866f82b385d60df947d71b67ac01a18b022015e3f02fd","schema_version":"1.0","event_id":"sha256:e58a1c3e316a3fe1c0d866f82b385d60df947d71b67ac01a18b022015e3f02fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6HWEOIAITREBDGKJM4THPONVZ/bundle.json","state_url":"https://pith.science/pith/P6HWEOIAITREBDGKJM4THPONVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6HWEOIAITREBDGKJM4THPONVZ/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":"2026-06-01T07:31:25Z","links":{"resolver":"https://pith.science/pith/P6HWEOIAITREBDGKJM4THPONVZ","bundle":"https://pith.science/pith/P6HWEOIAITREBDGKJM4THPONVZ/bundle.json","state":"https://pith.science/pith/P6HWEOIAITREBDGKJM4THPONVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6HWEOIAITREBDGKJM4THPONVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P6HWEOIAITREBDGKJM4THPONVZ","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":"84832a61feb1ae43c1b21db4171f72bf6512e37535219643a767cb11eeb33c96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T20:16:48Z","title_canon_sha256":"a8967f33e4b96de2001bd2bd95c4e47771ccab470fdcff1079d9769fac1a1c5d"},"schema_version":"1.0","source":{"id":"2605.12709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12709","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12709v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12709","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"P6HWEOIAITRE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"P6HWEOIAITREBDGK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"P6HWEOIA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e58a1c3e316a3fe1c0d866f82b385d60df947d71b67ac01a18b022015e3f02fd","target":"graph","created_at":"2026-05-18T03:09:49Z","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":"We show that SEC is a versatile tool for INR analysis, demonstrating its utility across three tasks: (1) a data-driven strategy (SEC-Conf) for hyperparameter selection that outperforms existing heuristics and is robust to model depth, (2) a reliable proxy for signal complexity, and (3) effective alignment of spectral biases across diverse INR architectures."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Spectral Energy Centroid computed from the target signal accurately predicts the optimal embedding frequency for an INR of arbitrary depth and architecture without requiring any training-time feedback."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Spectral Energy Centroid is a new metric that quantifies signal frequency and INR spectral bias, supporting better hyperparameter selection and cross-architecture analysis."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Spectral Energy Centroid computed from a target signal selects embedding frequencies that improve implicit neural representation performance regardless of model depth."}],"snapshot_sha256":"228c48eaf4e307292b472a6c0ff09739a2956912a01e41735496957ceca6d883"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0f430d9e1edd481e2ecbba9f2d6fb0a5cc32de2b851bc3a329534569316de71d"},"paper":{"abstract_excerpt":"Implicit Neural Representations (INRs) model continuous signals using multilayer perceptrons (MLPs), enabling compact, differentiable, and high-fidelity representations of data across diverse domains. However, due to the low-frequency bias of MLPs that prevents effective learning of small details, the model's frequency must be carefully tuned through the embedding layer. Prior work established that this tuning can be performed before training based on the target signal, but it did not account for the significant effect of model depth, indicating that our understanding of the relationship betwe","authors_text":"Adam Kania, Maciej Rut, Przemys{\\l}aw Spurek, Tomasz D\\k{a}dela","cross_cats":[],"headline":"Spectral Energy Centroid computed from a target signal selects embedding frequencies that improve implicit neural representation performance regardless of model depth.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T20:16:48Z","title":"Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations"},"references":{"count":23,"internal_anchors":2,"resolved_work":23,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Shenoy, and Steven H","work_id":"c3d81a28-946c-40e8-ab28-538954bb24c3","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A scalable Walsh-Hadamard regularizer to overcome the low-degree spectral bias of neural networks","work_id":"8948c3e9-9df3-4376-a1c5-099df3205a38","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Fresh: Frequency shifting for accelerated neural representation learning","work_id":"aba29de8-0807-411f-bed3-ce95987f12bb","year":2025},{"cited_arxiv_id":"1412.6980","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"J. Liu, D. Liu, W. Yang, S. Xia, X. Zhang, and Y . Dai. A comprehensive benchmark for single image compression artifact reduction.IEEE Transactions on Image Processing, 29:7845–7860, 2020","work_id":"6e891e92-e2ed-4ca1-bfea-7ef100f9d31b","year":2020}],"snapshot_sha256":"edf307ec8131a91f82851a219d9e45c39df5a3b64f6c628dfa1db929245820a2"},"source":{"id":"2605.12709","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:32:37.587626Z","id":"e97b4ed4-a29c-4be9-8027-c5baef2eda3e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Spectral Energy Centroid is a new metric that quantifies signal frequency and INR spectral bias, supporting better hyperparameter selection and cross-architecture analysis.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Spectral Energy Centroid computed from a target signal selects embedding frequencies that improve implicit neural representation performance regardless of model depth.","strongest_claim":"We show that SEC is a versatile tool for INR analysis, demonstrating its utility across three tasks: (1) a data-driven strategy (SEC-Conf) for hyperparameter selection that outperforms existing heuristics and is robust to model depth, (2) a reliable proxy for signal complexity, and (3) effective alignment of spectral biases across diverse INR architectures.","weakest_assumption":"That the Spectral Energy Centroid computed from the target signal accurately predicts the optimal embedding frequency for an INR of arbitrary depth and architecture without requiring any training-time feedback."}},"verdict_id":"e97b4ed4-a29c-4be9-8027-c5baef2eda3e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e99e0011040bcf6eb1923d33e728a20bae3395e2fecfc8a845e781b96a9946dc","target":"record","created_at":"2026-05-18T03:09:49Z","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":"84832a61feb1ae43c1b21db4171f72bf6512e37535219643a767cb11eeb33c96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T20:16:48Z","title_canon_sha256":"a8967f33e4b96de2001bd2bd95c4e47771ccab470fdcff1079d9769fac1a1c5d"},"schema_version":"1.0","source":{"id":"2605.12709","kind":"arxiv","version":1}},"canonical_sha256":"7f8f62390044e2408cca4b3933bdcdae4a61dbd3612e16d1269a3b9ea27e2a83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f8f62390044e2408cca4b3933bdcdae4a61dbd3612e16d1269a3b9ea27e2a83","first_computed_at":"2026-05-18T03:09:49.571962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:49.571962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b/XJEHTxWqkUFK8GdI/NKsPUhXCiEcwJSkcvkhJq4HwKzzFNd2ABj00t6wHbHmrmQjNWJy5iwwkW4bLRjO5iBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:49.572928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e99e0011040bcf6eb1923d33e728a20bae3395e2fecfc8a845e781b96a9946dc","sha256:e58a1c3e316a3fe1c0d866f82b385d60df947d71b67ac01a18b022015e3f02fd"],"state_sha256":"8cb08d47f4517da33f3b86d718c516d7c3a45b1b09c1788ac71f8c3b47cbde27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i7q0h17g4YFK89j7gByuzusHnJgjxOKWh3WKszyPA7ybN7XiwH71nnTuOzp86R9tM6PhdSeSBCmBqJm9U/I1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:31:25.851764Z","bundle_sha256":"6ad374660dd293ccfd31031109544083f8cb584688f5d83a7c36ff6a0b897ed1"}}