{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JNC4KRD3QZIGKA6N2T7JZOTG5G","short_pith_number":"pith:JNC4KRD3","canonical_record":{"source":{"id":"2402.04779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:01:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7070817cc7eed32921169cc556032acaf2546dfaae9be78df1e9085c5cc1fa4f","abstract_canon_sha256":"9872d156833d89c0ed034dbbcead43c14558a687d44afc368db9fbb5b7b804b3"},"schema_version":"1.0"},"canonical_sha256":"4b45c5447b86506503cdd4fe9cba66e9a410e4f079f0289c238c40c4e46ab2a1","source":{"kind":"arxiv","id":"2402.04779","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04779","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04779v1","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04779","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"JNC4KRD3QZIG","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"JNC4KRD3QZIGKA6N","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"JNC4KRD3","created_at":"2026-07-05T07:42:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JNC4KRD3QZIGKA6N2T7JZOTG5G","target":"record","payload":{"canonical_record":{"source":{"id":"2402.04779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:01:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7070817cc7eed32921169cc556032acaf2546dfaae9be78df1e9085c5cc1fa4f","abstract_canon_sha256":"9872d156833d89c0ed034dbbcead43c14558a687d44afc368db9fbb5b7b804b3"},"schema_version":"1.0"},"canonical_sha256":"4b45c5447b86506503cdd4fe9cba66e9a410e4f079f0289c238c40c4e46ab2a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:32.458634Z","signature_b64":"5It1HUyo4l/jisRMOWl8gv30flkZytyA9kEQ4Ck8HCgKOUEsYSFwWYMCkupZ915VuBesTCl0PfzJtY6PLi8TDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b45c5447b86506503cdd4fe9cba66e9a410e4f079f0289c238c40c4e46ab2a1","last_reissued_at":"2026-07-05T07:42:32.458152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:32.458152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.04779","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":"2026-07-05T07:42:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8VY8yZY7jg0DrXft/UOOUo81RDr9SN6STEL2+FKAVgiR1egU/444Tp4uHaACfnNC1Ym9Cn3GZFU6LLViOo9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:08:06.077202Z"},"content_sha256":"d457c900137ee845637dd033fa8dc5cf1a82f77c8117b489cdda60c8fc8a1219","schema_version":"1.0","event_id":"sha256:d457c900137ee845637dd033fa8dc5cf1a82f77c8117b489cdda60c8fc8a1219"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JNC4KRD3QZIGKA6N2T7JZOTG5G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StableMask: Refining Causal Masking in Decoder-only Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianhua Yao, Qiang Zhang, Qingyu Yin, Xiang Zhuang, Xiaoyu Shen, Xuzheng He, Yu Zhao","submitted_at":"2024-02-07T12:01:02Z","abstract_excerpt":"The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling. Despite its exceptional performance across various tasks, we have identified two limitations: First, it requires all attention scores to be non-zero and sum up to 1, even if the current embedding has sufficient self-contained information. This compels the model to assign disproportional excessive attention to specific tokens. Second, RPE-based Transformers are not universal approximators due to their limited capacity at encoding absolute positi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04779","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/2402.04779/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":"2026-07-05T07:42:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ec3VheTpbGpksOHzVgjF1mBAlyFdpEZ0DfK+F/gGlHBsK5t+x/brGuJDruj6e1ls2AlzlcJ4Z+rqzNTeEp0RDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:08:06.078217Z"},"content_sha256":"aad166f05a2a2db574a0cc5590528afa3d155e70e2b0910981203f9ebc3d94de","schema_version":"1.0","event_id":"sha256:aad166f05a2a2db574a0cc5590528afa3d155e70e2b0910981203f9ebc3d94de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G/bundle.json","state_url":"https://pith.science/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G/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":"2026-08-14T03:08:06Z","links":{"resolver":"https://pith.science/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G","bundle":"https://pith.science/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G/bundle.json","state":"https://pith.science/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JNC4KRD3QZIGKA6N2T7JZOTG5G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JNC4KRD3QZIGKA6N2T7JZOTG5G","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":"9872d156833d89c0ed034dbbcead43c14558a687d44afc368db9fbb5b7b804b3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:01:02Z","title_canon_sha256":"7070817cc7eed32921169cc556032acaf2546dfaae9be78df1e9085c5cc1fa4f"},"schema_version":"1.0","source":{"id":"2402.04779","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04779","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04779v1","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04779","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"JNC4KRD3QZIG","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"JNC4KRD3QZIGKA6N","created_at":"2026-07-05T07:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"JNC4KRD3","created_at":"2026-07-05T07:42:32Z"}],"graph_snapshots":[{"event_id":"sha256:aad166f05a2a2db574a0cc5590528afa3d155e70e2b0910981203f9ebc3d94de","target":"graph","created_at":"2026-07-05T07:42:32Z","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/2402.04779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling. Despite its exceptional performance across various tasks, we have identified two limitations: First, it requires all attention scores to be non-zero and sum up to 1, even if the current embedding has sufficient self-contained information. This compels the model to assign disproportional excessive attention to specific tokens. Second, RPE-based Transformers are not universal approximators due to their limited capacity at encoding absolute positi","authors_text":"Jianhua Yao, Qiang Zhang, Qingyu Yin, Xiang Zhuang, Xiaoyu Shen, Xuzheng He, Yu Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:01:02Z","title":"StableMask: Refining Causal Masking in Decoder-only Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04779","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:d457c900137ee845637dd033fa8dc5cf1a82f77c8117b489cdda60c8fc8a1219","target":"record","created_at":"2026-07-05T07:42:32Z","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":"9872d156833d89c0ed034dbbcead43c14558a687d44afc368db9fbb5b7b804b3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:01:02Z","title_canon_sha256":"7070817cc7eed32921169cc556032acaf2546dfaae9be78df1e9085c5cc1fa4f"},"schema_version":"1.0","source":{"id":"2402.04779","kind":"arxiv","version":1}},"canonical_sha256":"4b45c5447b86506503cdd4fe9cba66e9a410e4f079f0289c238c40c4e46ab2a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b45c5447b86506503cdd4fe9cba66e9a410e4f079f0289c238c40c4e46ab2a1","first_computed_at":"2026-07-05T07:42:32.458152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:32.458152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5It1HUyo4l/jisRMOWl8gv30flkZytyA9kEQ4Ck8HCgKOUEsYSFwWYMCkupZ915VuBesTCl0PfzJtY6PLi8TDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:32.458634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04779","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d457c900137ee845637dd033fa8dc5cf1a82f77c8117b489cdda60c8fc8a1219","sha256:aad166f05a2a2db574a0cc5590528afa3d155e70e2b0910981203f9ebc3d94de"],"state_sha256":"a3549f8c98247620d949d29b14aa87afb74a9583268ed8fd273c6a551d9acd84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNJ2Z7BiYFHkHR71Dk3YYvhd9lK96VvuDYcyvRr6lXjHPLrCfO05O7ICtmK3EK/NppyG+3qSwrZcMNWSvztMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:08:06.095170Z","bundle_sha256":"2dbfbd0e9917d13edc0c7c322ee48e707b26e83503080a2a59b7a0b93894dc99"}}