{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XPDE6J3CVT7YOY2LKWZZOEOX7L","short_pith_number":"pith:XPDE6J3C","canonical_record":{"source":{"id":"2004.14996","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:38:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b4b9b32d545df8e4effe8ba9005646bb3c0046a5ded941e73ee700ee5205d0fc","abstract_canon_sha256":"903ec7280ab76788e696039adc4a083f7c74eeb84a3eb44c45c5b242f940ac4e"},"schema_version":"1.0"},"canonical_sha256":"bbc64f2762acff87634b55b39711d7faeda0a0a6e197b2e05fbc172530a3b86b","source":{"kind":"arxiv","id":"2004.14996","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14996","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14996v2","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14996","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"pith_short_12","alias_value":"XPDE6J3CVT7Y","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"pith_short_16","alias_value":"XPDE6J3CVT7YOY2L","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"pith_short_8","alias_value":"XPDE6J3C","created_at":"2026-07-05T01:59:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XPDE6J3CVT7YOY2LKWZZOEOX7L","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14996","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:38:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b4b9b32d545df8e4effe8ba9005646bb3c0046a5ded941e73ee700ee5205d0fc","abstract_canon_sha256":"903ec7280ab76788e696039adc4a083f7c74eeb84a3eb44c45c5b242f940ac4e"},"schema_version":"1.0"},"canonical_sha256":"bbc64f2762acff87634b55b39711d7faeda0a0a6e197b2e05fbc172530a3b86b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:55.620038Z","signature_b64":"MPCmTs9dkd4N9pJUoHz8R76LEGDfT184BO0EJvOg8qax8vibip2NyIYrhEESaLxYb+aeg0WYgh7QKVDs5zj4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc64f2762acff87634b55b39711d7faeda0a0a6e197b2e05fbc172530a3b86b","last_reissued_at":"2026-07-05T01:59:55.619552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:55.619552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14996","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:59:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbeFJtibZqcdk0jJKpyB/vgV9m5jMVaTG7Xl2ksYK8kxUsDiPQXUSdgsxiopIe3ENURJTo28H+KAFD+FcwPfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:23:14.499361Z"},"content_sha256":"3a4c14516416bb267bc3449f5001bff7e7d7260cd10f6de0e49d6e46f98aefc6","schema_version":"1.0","event_id":"sha256:3a4c14516416bb267bc3449f5001bff7e7d7260cd10f6de0e49d6e46f98aefc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XPDE6J3CVT7YOY2LKWZZOEOX7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"He Bai, Jimmy Lin, Kun Xiong, Luchen Tan, Ming Li, Peng Shi, Wen Gao, Yuqing Xie","submitted_at":"2020-04-30T17:38:27Z","abstract_excerpt":"Transformers are powerful for sequence modeling. Nearly all state-of-the-art language models and pre-trained language models are based on the Transformer architecture. However, it distinguishes sequential tokens only with the token position index. We hypothesize that better contextual representations can be generated from the Transformer with richer positional information. To verify this, we propose a segment-aware Transformer (Segatron), by replacing the original token position encoding with a combined position encoding of paragraph, sentence, and token. We first introduce the segment-aware m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14996","kind":"arxiv","version":2},"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/2004.14996/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":"2026-07-05T01:59:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXhcbEq5h+TQbyoQ0NnGP5Z3YHBehAL6I0UsdDaL+dITgeOEYBONbk68sJXuaB3WNAlsQC5GVnLZoqfYdUhcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:23:14.499745Z"},"content_sha256":"8dce42a6ed71d94f211537c3cdd1497d77844fe7ca9d8d22610187c3f29ba929","schema_version":"1.0","event_id":"sha256:8dce42a6ed71d94f211537c3cdd1497d77844fe7ca9d8d22610187c3f29ba929"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L/bundle.json","state_url":"https://pith.science/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L/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":"2026-07-07T12:23:14Z","links":{"resolver":"https://pith.science/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L","bundle":"https://pith.science/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L/bundle.json","state":"https://pith.science/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPDE6J3CVT7YOY2LKWZZOEOX7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XPDE6J3CVT7YOY2LKWZZOEOX7L","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":"903ec7280ab76788e696039adc4a083f7c74eeb84a3eb44c45c5b242f940ac4e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:38:27Z","title_canon_sha256":"b4b9b32d545df8e4effe8ba9005646bb3c0046a5ded941e73ee700ee5205d0fc"},"schema_version":"1.0","source":{"id":"2004.14996","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14996","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14996v2","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14996","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"pith_short_12","alias_value":"XPDE6J3CVT7Y","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"pith_short_16","alias_value":"XPDE6J3CVT7YOY2L","created_at":"2026-07-05T01:59:55Z"},{"alias_kind":"pith_short_8","alias_value":"XPDE6J3C","created_at":"2026-07-05T01:59:55Z"}],"graph_snapshots":[{"event_id":"sha256:8dce42a6ed71d94f211537c3cdd1497d77844fe7ca9d8d22610187c3f29ba929","target":"graph","created_at":"2026-07-05T01:59:55Z","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/2004.14996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers are powerful for sequence modeling. Nearly all state-of-the-art language models and pre-trained language models are based on the Transformer architecture. However, it distinguishes sequential tokens only with the token position index. We hypothesize that better contextual representations can be generated from the Transformer with richer positional information. To verify this, we propose a segment-aware Transformer (Segatron), by replacing the original token position encoding with a combined position encoding of paragraph, sentence, and token. We first introduce the segment-aware m","authors_text":"He Bai, Jimmy Lin, Kun Xiong, Luchen Tan, Ming Li, Peng Shi, Wen Gao, Yuqing Xie","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:38:27Z","title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14996","kind":"arxiv","version":2},"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":"sha256:3a4c14516416bb267bc3449f5001bff7e7d7260cd10f6de0e49d6e46f98aefc6","target":"record","created_at":"2026-07-05T01:59:55Z","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":"903ec7280ab76788e696039adc4a083f7c74eeb84a3eb44c45c5b242f940ac4e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:38:27Z","title_canon_sha256":"b4b9b32d545df8e4effe8ba9005646bb3c0046a5ded941e73ee700ee5205d0fc"},"schema_version":"1.0","source":{"id":"2004.14996","kind":"arxiv","version":2}},"canonical_sha256":"bbc64f2762acff87634b55b39711d7faeda0a0a6e197b2e05fbc172530a3b86b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbc64f2762acff87634b55b39711d7faeda0a0a6e197b2e05fbc172530a3b86b","first_computed_at":"2026-07-05T01:59:55.619552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:55.619552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MPCmTs9dkd4N9pJUoHz8R76LEGDfT184BO0EJvOg8qax8vibip2NyIYrhEESaLxYb+aeg0WYgh7QKVDs5zj4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:55.620038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14996","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a4c14516416bb267bc3449f5001bff7e7d7260cd10f6de0e49d6e46f98aefc6","sha256:8dce42a6ed71d94f211537c3cdd1497d77844fe7ca9d8d22610187c3f29ba929"],"state_sha256":"7e301449b5011f946defc676da7198cc432f3aa2d2ad0fd1e89994ad307494d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/Rkj1pse+bBHvXjdYDtfvm0NyaesH4cXSGX+J1N7zYG6fCS1MyTyePE6Oy9IB8/U+pFFIjo9z4t0yp9WKsABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:23:14.501945Z","bundle_sha256":"c5408f39478c3e78f2e305821d91e73ce54d2b641a2f6a8e072876f0d7a1a92b"}}