{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SCDOKSZXMBOMTZN2KACSJWKEU4","short_pith_number":"pith:SCDOKSZX","canonical_record":{"source":{"id":"2305.12289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T21:52:24Z","cross_cats_sorted":[],"title_canon_sha256":"cbe54e31d4ff433903a0163aadab0d04849506a992b605387e4d0d99ae975013","abstract_canon_sha256":"697e01a6118a4cc82f42ab568424bb8552c64ace2327db22ea06e0328042c789"},"schema_version":"1.0"},"canonical_sha256":"9086e54b37605cc9e5ba500524d944a72524b045d8651c2bab14eb0a438b28a0","source":{"kind":"arxiv","id":"2305.12289","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12289","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12289v1","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12289","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"SCDOKSZXMBOM","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"pith_short_16","alias_value":"SCDOKSZXMBOMTZN2","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"pith_short_8","alias_value":"SCDOKSZX","created_at":"2026-07-05T06:12:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SCDOKSZXMBOMTZN2KACSJWKEU4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.12289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T21:52:24Z","cross_cats_sorted":[],"title_canon_sha256":"cbe54e31d4ff433903a0163aadab0d04849506a992b605387e4d0d99ae975013","abstract_canon_sha256":"697e01a6118a4cc82f42ab568424bb8552c64ace2327db22ea06e0328042c789"},"schema_version":"1.0"},"canonical_sha256":"9086e54b37605cc9e5ba500524d944a72524b045d8651c2bab14eb0a438b28a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:08.876642Z","signature_b64":"HHtTxhHUxv97+R6gukS7MP5PHd/Q7NUz/OyRPKsJdsL6FL3K2G+3ShFG6WxIoaTWnS9MwDTp5Iyt3Jf6/f0UCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9086e54b37605cc9e5ba500524d944a72524b045d8651c2bab14eb0a438b28a0","last_reissued_at":"2026-07-05T06:12:08.876176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:08.876176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.12289","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":"2026-07-05T06:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DjkhnMKAZeNBkqxabWa0HrFjsuiwfHkazaBJJtpJ2tXCcEEEJocBeAxkU7/hPSJgzsitTEGdhpNm3oXhIdICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:03:48.701398Z"},"content_sha256":"470e95a2d2205f6d0dd9d42cafa98ed3d878525eeab879c40859de6a55a516e3","schema_version":"1.0","event_id":"sha256:470e95a2d2205f6d0dd9d42cafa98ed3d878525eeab879c40859de6a55a516e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SCDOKSZXMBOMTZN2KACSJWKEU4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alolika Gon, Andrew McCallum, Haw-Shiuan Chang, Hong Yu, Zonghai Yao","submitted_at":"2023-05-20T21:52:24Z","abstract_excerpt":"Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant nowadays? In this study, we discover that the answers to both questions are no. This is because the softmax bottleneck sometimes prevents the LMs from predicting the desired distribution and the pointer networks can be used to break the bottleneck efficiently. Based on the finding, we propose several softmax alternatives by simplifying the pointer networks and ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12289","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/2305.12289/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":"2026-07-05T06:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f02pehp7RuQJqr/wwJZ/ghGdnYiP+0QNzmDnJjzooZGaVzhYaYwiuU2nMkRX/mBoSDZjEM06IY0OmIJcfcHHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:03:48.701776Z"},"content_sha256":"7256394f4040939ec34b4260782fef10131609503274a1866a0158d15372637f","schema_version":"1.0","event_id":"sha256:7256394f4040939ec34b4260782fef10131609503274a1866a0158d15372637f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCDOKSZXMBOMTZN2KACSJWKEU4/bundle.json","state_url":"https://pith.science/pith/SCDOKSZXMBOMTZN2KACSJWKEU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCDOKSZXMBOMTZN2KACSJWKEU4/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":"2026-08-03T22:03:48Z","links":{"resolver":"https://pith.science/pith/SCDOKSZXMBOMTZN2KACSJWKEU4","bundle":"https://pith.science/pith/SCDOKSZXMBOMTZN2KACSJWKEU4/bundle.json","state":"https://pith.science/pith/SCDOKSZXMBOMTZN2KACSJWKEU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCDOKSZXMBOMTZN2KACSJWKEU4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SCDOKSZXMBOMTZN2KACSJWKEU4","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":"697e01a6118a4cc82f42ab568424bb8552c64ace2327db22ea06e0328042c789","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T21:52:24Z","title_canon_sha256":"cbe54e31d4ff433903a0163aadab0d04849506a992b605387e4d0d99ae975013"},"schema_version":"1.0","source":{"id":"2305.12289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12289","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12289v1","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12289","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"SCDOKSZXMBOM","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"pith_short_16","alias_value":"SCDOKSZXMBOMTZN2","created_at":"2026-07-05T06:12:08Z"},{"alias_kind":"pith_short_8","alias_value":"SCDOKSZX","created_at":"2026-07-05T06:12:08Z"}],"graph_snapshots":[{"event_id":"sha256:7256394f4040939ec34b4260782fef10131609503274a1866a0158d15372637f","target":"graph","created_at":"2026-07-05T06:12:08Z","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/2305.12289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant nowadays? In this study, we discover that the answers to both questions are no. This is because the softmax bottleneck sometimes prevents the LMs from predicting the desired distribution and the pointer networks can be used to break the bottleneck efficiently. Based on the finding, we propose several softmax alternatives by simplifying the pointer networks and ac","authors_text":"Alolika Gon, Andrew McCallum, Haw-Shiuan Chang, Hong Yu, Zonghai Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T21:52:24Z","title":"Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12289","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":"sha256:470e95a2d2205f6d0dd9d42cafa98ed3d878525eeab879c40859de6a55a516e3","target":"record","created_at":"2026-07-05T06:12:08Z","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":"697e01a6118a4cc82f42ab568424bb8552c64ace2327db22ea06e0328042c789","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T21:52:24Z","title_canon_sha256":"cbe54e31d4ff433903a0163aadab0d04849506a992b605387e4d0d99ae975013"},"schema_version":"1.0","source":{"id":"2305.12289","kind":"arxiv","version":1}},"canonical_sha256":"9086e54b37605cc9e5ba500524d944a72524b045d8651c2bab14eb0a438b28a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9086e54b37605cc9e5ba500524d944a72524b045d8651c2bab14eb0a438b28a0","first_computed_at":"2026-07-05T06:12:08.876176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:08.876176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHtTxhHUxv97+R6gukS7MP5PHd/Q7NUz/OyRPKsJdsL6FL3K2G+3ShFG6WxIoaTWnS9MwDTp5Iyt3Jf6/f0UCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:08.876642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:470e95a2d2205f6d0dd9d42cafa98ed3d878525eeab879c40859de6a55a516e3","sha256:7256394f4040939ec34b4260782fef10131609503274a1866a0158d15372637f"],"state_sha256":"2ead902f64067b11e7cfc087e2c547f8ec8ab759bf7e3e3a578d3a99d1869985"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GKH1FLikCxORrxtOFF9O91JL7YS/IZy00ZXKWj7qNio8uFkMlVHE+i+ARXJthlJMK+VVwvt/LRJ92xwir4FCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:03:48.704573Z","bundle_sha256":"023575dfa115b497339a7ada005534f6324902354868c5d4189365a6cf639930"}}