{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H3EOQKDOKW45CKHHLKMKUFCHG3","short_pith_number":"pith:H3EOQKDO","canonical_record":{"source":{"id":"2307.09084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T09:06:35Z","cross_cats_sorted":[],"title_canon_sha256":"4242841c7bea813d08b3ca410752b473c8bde7d69196562f96b03d4c5414a0ec","abstract_canon_sha256":"7f74afc5acf91144607f4c3e8fc5f9d13595e12f6a8123922bd88c755134db50"},"schema_version":"1.0"},"canonical_sha256":"3ec8e8286e55b9d128e75a98aa144736e4d3944da746c9caf07793a5f3afeffe","source":{"kind":"arxiv","id":"2307.09084","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09084","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09084v1","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09084","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"pith_short_12","alias_value":"H3EOQKDOKW45","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"H3EOQKDOKW45CKHH","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"H3EOQKDO","created_at":"2026-07-05T06:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H3EOQKDOKW45CKHHLKMKUFCHG3","target":"record","payload":{"canonical_record":{"source":{"id":"2307.09084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T09:06:35Z","cross_cats_sorted":[],"title_canon_sha256":"4242841c7bea813d08b3ca410752b473c8bde7d69196562f96b03d4c5414a0ec","abstract_canon_sha256":"7f74afc5acf91144607f4c3e8fc5f9d13595e12f6a8123922bd88c755134db50"},"schema_version":"1.0"},"canonical_sha256":"3ec8e8286e55b9d128e75a98aa144736e4d3944da746c9caf07793a5f3afeffe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:39.079935Z","signature_b64":"YnHq0dTqRxrhNsgZAZFdYHhmUm2mPxzGRYo7tYyxHQIU131oyYGLjXIjIydukRxL9yDUDMPXhuMSA25NGelzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ec8e8286e55b9d128e75a98aa144736e4d3944da746c9caf07793a5f3afeffe","last_reissued_at":"2026-07-05T06:31:39.079520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:39.079520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.09084","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":"2026-07-05T06:31:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7F8VnJ94MkYZFEI8EcXAZvWFIGd2uNDPst0icdHJLKJkVQ3N8WCVLnhpB3pP26YUZ94cxTF5I68MffktQ2YSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:30:16.481062Z"},"content_sha256":"73301284d13ec9e86073e6af212346d617d7a0518ede6a2d487a03177f17adeb","schema_version":"1.0","event_id":"sha256:73301284d13ec9e86073e6af212346d617d7a0518ede6a2d487a03177f17adeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H3EOQKDOKW45CKHHLKMKUFCHG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention over pre-trained Sentence Embeddings for Long Document Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amine Abdaoui, Sourav Dutta","submitted_at":"2023-07-18T09:06:35Z","abstract_excerpt":"Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either by reducing the cost of the self-attention computation or by modeling smaller sequences and combining them through a recurrence mechanism or using a new transformer model. In this paper, we suggest to take advantage of pre-trained sentence transformers to start from semantically meaningful embeddings of the individual sentences, and then combine them through"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09084","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/2307.09084/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":"2026-07-05T06:31:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSqrsJFAj+w4G8YbAkCIzu8wTwPpNu5/HgwKPX/TXfs18t8g/sms68jqH1go9qjKhr2x5efwvL4x4LBlN3NzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:30:16.482128Z"},"content_sha256":"6f05d4493b643a665159888649566251b95fb5df87cb916878e52c59bde955fc","schema_version":"1.0","event_id":"sha256:6f05d4493b643a665159888649566251b95fb5df87cb916878e52c59bde955fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3EOQKDOKW45CKHHLKMKUFCHG3/bundle.json","state_url":"https://pith.science/pith/H3EOQKDOKW45CKHHLKMKUFCHG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3EOQKDOKW45CKHHLKMKUFCHG3/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":"2026-08-18T18:30:16Z","links":{"resolver":"https://pith.science/pith/H3EOQKDOKW45CKHHLKMKUFCHG3","bundle":"https://pith.science/pith/H3EOQKDOKW45CKHHLKMKUFCHG3/bundle.json","state":"https://pith.science/pith/H3EOQKDOKW45CKHHLKMKUFCHG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3EOQKDOKW45CKHHLKMKUFCHG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H3EOQKDOKW45CKHHLKMKUFCHG3","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":"7f74afc5acf91144607f4c3e8fc5f9d13595e12f6a8123922bd88c755134db50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T09:06:35Z","title_canon_sha256":"4242841c7bea813d08b3ca410752b473c8bde7d69196562f96b03d4c5414a0ec"},"schema_version":"1.0","source":{"id":"2307.09084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09084","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09084v1","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09084","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"pith_short_12","alias_value":"H3EOQKDOKW45","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"H3EOQKDOKW45CKHH","created_at":"2026-07-05T06:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"H3EOQKDO","created_at":"2026-07-05T06:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:6f05d4493b643a665159888649566251b95fb5df87cb916878e52c59bde955fc","target":"graph","created_at":"2026-07-05T06:31:39Z","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/2307.09084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either by reducing the cost of the self-attention computation or by modeling smaller sequences and combining them through a recurrence mechanism or using a new transformer model. In this paper, we suggest to take advantage of pre-trained sentence transformers to start from semantically meaningful embeddings of the individual sentences, and then combine them through","authors_text":"Amine Abdaoui, Sourav Dutta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T09:06:35Z","title":"Attention over pre-trained Sentence Embeddings for Long Document Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09084","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":"sha256:73301284d13ec9e86073e6af212346d617d7a0518ede6a2d487a03177f17adeb","target":"record","created_at":"2026-07-05T06:31:39Z","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":"7f74afc5acf91144607f4c3e8fc5f9d13595e12f6a8123922bd88c755134db50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T09:06:35Z","title_canon_sha256":"4242841c7bea813d08b3ca410752b473c8bde7d69196562f96b03d4c5414a0ec"},"schema_version":"1.0","source":{"id":"2307.09084","kind":"arxiv","version":1}},"canonical_sha256":"3ec8e8286e55b9d128e75a98aa144736e4d3944da746c9caf07793a5f3afeffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ec8e8286e55b9d128e75a98aa144736e4d3944da746c9caf07793a5f3afeffe","first_computed_at":"2026-07-05T06:31:39.079520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:31:39.079520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YnHq0dTqRxrhNsgZAZFdYHhmUm2mPxzGRYo7tYyxHQIU131oyYGLjXIjIydukRxL9yDUDMPXhuMSA25NGelzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:31:39.079935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.09084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73301284d13ec9e86073e6af212346d617d7a0518ede6a2d487a03177f17adeb","sha256:6f05d4493b643a665159888649566251b95fb5df87cb916878e52c59bde955fc"],"state_sha256":"82ed73a821697f97067c8d775f3591e9c84e26c92fb721668b7f038a00a3980b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcanppC8lh8n7CvdhzYM4jFbB9lPzusiHsI88iVb1++i3W9ryIkvwbOYudLp2gXOzX/TsTxwsDG19kovJ+ypCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:30:16.494321Z","bundle_sha256":"b4b67fa3b735251396e3974da7aa8aa0ceff27f19ac938ad7bbfbcdb96e707d3"}}