{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5BLKGXCA3USZNBOJYUOZYLU4XI","short_pith_number":"pith:5BLKGXCA","canonical_record":{"source":{"id":"2502.09287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T13:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"683c60355e92c8db2e8ec2598a5ee5462751e9a3774ca642fe13568001200d59","abstract_canon_sha256":"042967dd067f2a836aa79437a946f6a9e948803d68355540c152493c53ea7648"},"schema_version":"1.0"},"canonical_sha256":"e856a35c40dd259685c9c51d9c2e9cba3a9a0a54641f14b0b251cb702f8d9542","source":{"kind":"arxiv","id":"2502.09287","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09287","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09287v1","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09287","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"5BLKGXCA3USZ","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"5BLKGXCA3USZNBOJ","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"5BLKGXCA","created_at":"2026-07-05T10:13:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5BLKGXCA3USZNBOJYUOZYLU4XI","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T13:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"683c60355e92c8db2e8ec2598a5ee5462751e9a3774ca642fe13568001200d59","abstract_canon_sha256":"042967dd067f2a836aa79437a946f6a9e948803d68355540c152493c53ea7648"},"schema_version":"1.0"},"canonical_sha256":"e856a35c40dd259685c9c51d9c2e9cba3a9a0a54641f14b0b251cb702f8d9542","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:54.929521Z","signature_b64":"H+fpCaIM1tZAbBJx8O4F/yDtBjQqtAXmu8mHSmj1Pd/4ko0IWQB1CWFWb1e/Qt7ZR5wCJ/Ld0aaCBDqX7M3aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e856a35c40dd259685c9c51d9c2e9cba3a9a0a54641f14b0b251cb702f8d9542","last_reissued_at":"2026-07-05T10:13:54.929031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:54.929031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09287","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":"2026-07-05T10:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhuCbUpFa1sJ6DhI4LAR1lKf9mr8fP2B7JE8pV43PaXclUZsJ7QmgKXSwi6bTixwar2UpXzDzj7qMPeR9MvzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:48:56.602630Z"},"content_sha256":"8e5e3c6786ee3ff3e4fcc51751177aa9878ffe9069e3ade694f687a1a2cc3492","schema_version":"1.0","event_id":"sha256:8e5e3c6786ee3ff3e4fcc51751177aa9878ffe9069e3ade694f687a1a2cc3492"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5BLKGXCA3USZNBOJYUOZYLU4XI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Uncertainty Principle for Linear Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Fran\\c{c}ois, Antonio Orvieto, Francis Bach","submitted_at":"2025-02-13T13:01:46Z","abstract_excerpt":"We consider linear recurrent neural networks, which have become a key building block of sequence modeling due to their ability for stable and effective long-range modeling. In this paper, we aim at characterizing this ability on a simple but core copy task, whose goal is to build a linear filter of order $S$ that approximates the filter that looks $K$ time steps in the past (which we refer to as the shift-$K$ filter), where $K$ is larger than $S$. Using classical signal models and quadratic cost, we fully characterize the problem by providing lower bounds of approximation, as well as explicit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09287","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/2502.09287/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zHJU57ptu58AtAwYBm62vpf8fgq+8QvrpJSYcfCDxk2Q5sNvEsdal8BnflEkPuufjv8ncu1iqJTNIOjzHF63DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:48:56.603334Z"},"content_sha256":"df44851632712821fe22dd9446511d57c18a2d58086ada517cfb8689a4b33725","schema_version":"1.0","event_id":"sha256:df44851632712821fe22dd9446511d57c18a2d58086ada517cfb8689a4b33725"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BLKGXCA3USZNBOJYUOZYLU4XI/bundle.json","state_url":"https://pith.science/pith/5BLKGXCA3USZNBOJYUOZYLU4XI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BLKGXCA3USZNBOJYUOZYLU4XI/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":"2026-08-18T15:48:56Z","links":{"resolver":"https://pith.science/pith/5BLKGXCA3USZNBOJYUOZYLU4XI","bundle":"https://pith.science/pith/5BLKGXCA3USZNBOJYUOZYLU4XI/bundle.json","state":"https://pith.science/pith/5BLKGXCA3USZNBOJYUOZYLU4XI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BLKGXCA3USZNBOJYUOZYLU4XI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5BLKGXCA3USZNBOJYUOZYLU4XI","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":"042967dd067f2a836aa79437a946f6a9e948803d68355540c152493c53ea7648","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T13:01:46Z","title_canon_sha256":"683c60355e92c8db2e8ec2598a5ee5462751e9a3774ca642fe13568001200d59"},"schema_version":"1.0","source":{"id":"2502.09287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09287","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09287v1","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09287","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"5BLKGXCA3USZ","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"5BLKGXCA3USZNBOJ","created_at":"2026-07-05T10:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"5BLKGXCA","created_at":"2026-07-05T10:13:54Z"}],"graph_snapshots":[{"event_id":"sha256:df44851632712821fe22dd9446511d57c18a2d58086ada517cfb8689a4b33725","target":"graph","created_at":"2026-07-05T10:13:54Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.09287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider linear recurrent neural networks, which have become a key building block of sequence modeling due to their ability for stable and effective long-range modeling. In this paper, we aim at characterizing this ability on a simple but core copy task, whose goal is to build a linear filter of order $S$ that approximates the filter that looks $K$ time steps in the past (which we refer to as the shift-$K$ filter), where $K$ is larger than $S$. Using classical signal models and quadratic cost, we fully characterize the problem by providing lower bounds of approximation, as well as explicit ","authors_text":"Alexandre Fran\\c{c}ois, Antonio Orvieto, Francis Bach","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T13:01:46Z","title":"An Uncertainty Principle for Linear Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09287","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e5e3c6786ee3ff3e4fcc51751177aa9878ffe9069e3ade694f687a1a2cc3492","target":"record","created_at":"2026-07-05T10:13:54Z","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":"042967dd067f2a836aa79437a946f6a9e948803d68355540c152493c53ea7648","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T13:01:46Z","title_canon_sha256":"683c60355e92c8db2e8ec2598a5ee5462751e9a3774ca642fe13568001200d59"},"schema_version":"1.0","source":{"id":"2502.09287","kind":"arxiv","version":1}},"canonical_sha256":"e856a35c40dd259685c9c51d9c2e9cba3a9a0a54641f14b0b251cb702f8d9542","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e856a35c40dd259685c9c51d9c2e9cba3a9a0a54641f14b0b251cb702f8d9542","first_computed_at":"2026-07-05T10:13:54.929031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:54.929031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H+fpCaIM1tZAbBJx8O4F/yDtBjQqtAXmu8mHSmj1Pd/4ko0IWQB1CWFWb1e/Qt7ZR5wCJ/Ld0aaCBDqX7M3aAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:54.929521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e5e3c6786ee3ff3e4fcc51751177aa9878ffe9069e3ade694f687a1a2cc3492","sha256:df44851632712821fe22dd9446511d57c18a2d58086ada517cfb8689a4b33725"],"state_sha256":"8aca004a686c8c420620191c355303464650f71772e3dcda3317cdf4c455cdee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXS4u7m1Npy1yxYbxf2IT2RtLmeB+2Fx0NjpIZFtDG/KfGNUWLWOgYhd3q8uLIdOsC5BEqkIzlZ8g2UXN2iiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:48:56.609535Z","bundle_sha256":"52c6ce20c01f94d04588b640f4c8e2dad57bb085d208555bb15e71fe3cb70fca"}}