{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DGZ3ZJ4DBWZD5XDGNVHDQCBPCA","short_pith_number":"pith:DGZ3ZJ4D","canonical_record":{"source":{"id":"2311.05089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T01:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5075181bd392cf770f09f45ba6ac2e3840f58fe0c595a4ee4108291cfa17cfc","abstract_canon_sha256":"017e65c1f8e68ffc19fc6cf4472f6d1a5c6f5a4ab5bdb33750395eb84c958d8a"},"schema_version":"1.0"},"canonical_sha256":"19b3bca7830db23edc666d4e38082f101fa01669f4bb350ee520ce1b6a5562c7","source":{"kind":"arxiv","id":"2311.05089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05089","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05089v1","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05089","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"DGZ3ZJ4DBWZD","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"DGZ3ZJ4DBWZD5XDG","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"DGZ3ZJ4D","created_at":"2026-07-05T07:10:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DGZ3ZJ4DBWZD5XDGNVHDQCBPCA","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T01:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5075181bd392cf770f09f45ba6ac2e3840f58fe0c595a4ee4108291cfa17cfc","abstract_canon_sha256":"017e65c1f8e68ffc19fc6cf4472f6d1a5c6f5a4ab5bdb33750395eb84c958d8a"},"schema_version":"1.0"},"canonical_sha256":"19b3bca7830db23edc666d4e38082f101fa01669f4bb350ee520ce1b6a5562c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:54.341038Z","signature_b64":"9EPkqJdWg7wP1PBeh6gIUkPyOn6upugxBV0Q6PjqPhHRiNAwoRQ8E6xK8IdysnnKI0CzZVKb0mC6d0m7aCiACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19b3bca7830db23edc666d4e38082f101fa01669f4bb350ee520ce1b6a5562c7","last_reissued_at":"2026-07-05T07:10:54.340650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:54.340650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05089","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":"2026-07-05T07:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+OwlUbpH7rlQLT25pl3nnwgp/H+KdV5ZWSJOTHDLq9tkKTlQm1zQNHfzsv9vrqSUlOSwlDAi5LiASQpfXu/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:09:17.909933Z"},"content_sha256":"612f8233f22fd2614b5643d44a375cb6b9782be52be4692966c97bbf7f67f71a","schema_version":"1.0","event_id":"sha256:612f8233f22fd2614b5643d44a375cb6b9782be52be4692966c97bbf7f67f71a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DGZ3ZJ4DBWZD5XDGNVHDQCBPCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniele Giofr\\'e, Sneha Ghantasala","submitted_at":"2023-11-09T01:27:54Z","abstract_excerpt":"Since its introduction, the transformers architecture has seen great adoption in NLP applications, but it also has limitations. Although the self-attention mechanism allows for generating very rich representations of the input text, its effectiveness may be limited in specialized domains such as legal, where, for example, language models often have to process very long texts. In this paper, we explore alternatives to replace the attention-based layers with simpler token-mixing mechanisms: Hartley and Fourier transforms. Using these non-parametric techniques, we train models with long input doc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05089","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/2311.05089/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":"2026-07-05T07:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwibCcDHVrSjl4LdYn/O2XOGc6zBBDn+KxlqhXWCu198ZpkKVhF/tN2onxA1psyr+PA33V5k2hMoR/op2k8+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:09:17.910407Z"},"content_sha256":"abb2910a3868a2eb678e47c5016362ce3b8b9f5e68dbcc6f68a4b292c7a4143b","schema_version":"1.0","event_id":"sha256:abb2910a3868a2eb678e47c5016362ce3b8b9f5e68dbcc6f68a4b292c7a4143b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA/bundle.json","state_url":"https://pith.science/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA/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":"2026-07-07T14:09:17Z","links":{"resolver":"https://pith.science/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA","bundle":"https://pith.science/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA/bundle.json","state":"https://pith.science/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGZ3ZJ4DBWZD5XDGNVHDQCBPCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DGZ3ZJ4DBWZD5XDGNVHDQCBPCA","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":"017e65c1f8e68ffc19fc6cf4472f6d1a5c6f5a4ab5bdb33750395eb84c958d8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T01:27:54Z","title_canon_sha256":"e5075181bd392cf770f09f45ba6ac2e3840f58fe0c595a4ee4108291cfa17cfc"},"schema_version":"1.0","source":{"id":"2311.05089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05089","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05089v1","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05089","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"DGZ3ZJ4DBWZD","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"DGZ3ZJ4DBWZD5XDG","created_at":"2026-07-05T07:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"DGZ3ZJ4D","created_at":"2026-07-05T07:10:54Z"}],"graph_snapshots":[{"event_id":"sha256:abb2910a3868a2eb678e47c5016362ce3b8b9f5e68dbcc6f68a4b292c7a4143b","target":"graph","created_at":"2026-07-05T07:10:54Z","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/2311.05089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since its introduction, the transformers architecture has seen great adoption in NLP applications, but it also has limitations. Although the self-attention mechanism allows for generating very rich representations of the input text, its effectiveness may be limited in specialized domains such as legal, where, for example, language models often have to process very long texts. In this paper, we explore alternatives to replace the attention-based layers with simpler token-mixing mechanisms: Hartley and Fourier transforms. Using these non-parametric techniques, we train models with long input doc","authors_text":"Daniele Giofr\\'e, Sneha Ghantasala","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T01:27:54Z","title":"Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05089","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":"sha256:612f8233f22fd2614b5643d44a375cb6b9782be52be4692966c97bbf7f67f71a","target":"record","created_at":"2026-07-05T07:10:54Z","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":"017e65c1f8e68ffc19fc6cf4472f6d1a5c6f5a4ab5bdb33750395eb84c958d8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T01:27:54Z","title_canon_sha256":"e5075181bd392cf770f09f45ba6ac2e3840f58fe0c595a4ee4108291cfa17cfc"},"schema_version":"1.0","source":{"id":"2311.05089","kind":"arxiv","version":1}},"canonical_sha256":"19b3bca7830db23edc666d4e38082f101fa01669f4bb350ee520ce1b6a5562c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19b3bca7830db23edc666d4e38082f101fa01669f4bb350ee520ce1b6a5562c7","first_computed_at":"2026-07-05T07:10:54.340650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:54.340650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9EPkqJdWg7wP1PBeh6gIUkPyOn6upugxBV0Q6PjqPhHRiNAwoRQ8E6xK8IdysnnKI0CzZVKb0mC6d0m7aCiACA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:54.341038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:612f8233f22fd2614b5643d44a375cb6b9782be52be4692966c97bbf7f67f71a","sha256:abb2910a3868a2eb678e47c5016362ce3b8b9f5e68dbcc6f68a4b292c7a4143b"],"state_sha256":"d1b6a70b43d0eb3be773570899de39a0ab51dfefc01006ec2d4b5209464e4feb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aP7wuhMFfnIR2EgjDsf7b9oYSEcHB68B8vZyEIveQp9vN+4Dp3ZChp8vlEvmaqwLj0RqYcNjX6LRGMLsvzaRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:09:17.913135Z","bundle_sha256":"884c583dcfed1acf6d380e312ab6e3ad729a9af64b70730f945323f97161f27c"}}