{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WLHOYRRI6QMBPMG27HHHPDEDDP","short_pith_number":"pith:WLHOYRRI","canonical_record":{"source":{"id":"1705.04304","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-11T17:39:35Z","cross_cats_sorted":[],"title_canon_sha256":"371f5643d159a9daec925add0dc795f3e90be32c4d5c9b3ebc5d3a2428793c3f","abstract_canon_sha256":"0cae99058ce7213d67dd2a92432286e6efda84bf70181e0d52b86b94c49a3bde"},"schema_version":"1.0"},"canonical_sha256":"b2ceec4628f41817b0daf9ce778c831bec53387b42875695f9e67c56d0468bc4","source":{"kind":"arxiv","id":"1705.04304","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04304","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04304v3","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04304","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"WLHOYRRI6QMB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WLHOYRRI6QMBPMG2","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WLHOYRRI","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WLHOYRRI6QMBPMG27HHHPDEDDP","target":"record","payload":{"canonical_record":{"source":{"id":"1705.04304","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-11T17:39:35Z","cross_cats_sorted":[],"title_canon_sha256":"371f5643d159a9daec925add0dc795f3e90be32c4d5c9b3ebc5d3a2428793c3f","abstract_canon_sha256":"0cae99058ce7213d67dd2a92432286e6efda84bf70181e0d52b86b94c49a3bde"},"schema_version":"1.0"},"canonical_sha256":"b2ceec4628f41817b0daf9ce778c831bec53387b42875695f9e67c56d0468bc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:44.866870Z","signature_b64":"7luZHhi+jxMuGff+HYINWI/PrdOO2GoQ/OStloLUd4VzZJ9H3aBcEJs3Zj+4KFvPVdelCYpAK6cM+IH3ToCwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2ceec4628f41817b0daf9ce778c831bec53387b42875695f9e67c56d0468bc4","last_reissued_at":"2026-05-18T00:30:44.866246Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:44.866246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.04304","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSYkJij8xC6gvYRHgJeWfUTAriT83HeWcwxn4MW3PYJlNi5YBSclaIFPN3f+5ylRP5cWhBtXc853y+MJuko1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:40:55.306881Z"},"content_sha256":"5750b7fc00f718f377a4ef55f8fe173b5742bf05c5f8fc4ef8eb3ca16b8148dc","schema_version":"1.0","event_id":"sha256:5750b7fc00f718f377a4ef55f8fe173b5742bf05c5f8fc4ef8eb3ca16b8148dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WLHOYRRI6QMBPMG27HHHPDEDDP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Deep Reinforced Model for Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Richard Socher, Romain Paulus","submitted_at":"2017-05-11T17:39:35Z","abstract_excerpt":"Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. For longer documents and summaries however these models often include repetitive and incoherent phrases. We introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL). Models trained only with supervised learning often exhibit \"exposure bias\" - they assume ground truth i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04304","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JOf0TCDA7Jmxn8tP+JtpkJbGm/Yc/ZhS2aci7M8nX1xnjR0civGFD015azTf9yNxG4YRAm6z6AhltoCPHMn4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:40:55.307256Z"},"content_sha256":"d1d0846bc17290a00cc8911812bb25d710e1cd7af1d153e87754752c0fd7ef73","schema_version":"1.0","event_id":"sha256:d1d0846bc17290a00cc8911812bb25d710e1cd7af1d153e87754752c0fd7ef73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLHOYRRI6QMBPMG27HHHPDEDDP/bundle.json","state_url":"https://pith.science/pith/WLHOYRRI6QMBPMG27HHHPDEDDP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLHOYRRI6QMBPMG27HHHPDEDDP/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":"2026-05-19T10:40:55Z","links":{"resolver":"https://pith.science/pith/WLHOYRRI6QMBPMG27HHHPDEDDP","bundle":"https://pith.science/pith/WLHOYRRI6QMBPMG27HHHPDEDDP/bundle.json","state":"https://pith.science/pith/WLHOYRRI6QMBPMG27HHHPDEDDP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLHOYRRI6QMBPMG27HHHPDEDDP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WLHOYRRI6QMBPMG27HHHPDEDDP","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":"0cae99058ce7213d67dd2a92432286e6efda84bf70181e0d52b86b94c49a3bde","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-11T17:39:35Z","title_canon_sha256":"371f5643d159a9daec925add0dc795f3e90be32c4d5c9b3ebc5d3a2428793c3f"},"schema_version":"1.0","source":{"id":"1705.04304","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04304","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04304v3","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04304","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"WLHOYRRI6QMB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WLHOYRRI6QMBPMG2","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WLHOYRRI","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:d1d0846bc17290a00cc8911812bb25d710e1cd7af1d153e87754752c0fd7ef73","target":"graph","created_at":"2026-05-18T00:30:44Z","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"},"paper":{"abstract_excerpt":"Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. For longer documents and summaries however these models often include repetitive and incoherent phrases. We introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL). Models trained only with supervised learning often exhibit \"exposure bias\" - they assume ground truth i","authors_text":"Caiming Xiong, Richard Socher, Romain Paulus","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-11T17:39:35Z","title":"A Deep Reinforced Model for Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04304","kind":"arxiv","version":3},"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":"sha256:5750b7fc00f718f377a4ef55f8fe173b5742bf05c5f8fc4ef8eb3ca16b8148dc","target":"record","created_at":"2026-05-18T00:30:44Z","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":"0cae99058ce7213d67dd2a92432286e6efda84bf70181e0d52b86b94c49a3bde","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-11T17:39:35Z","title_canon_sha256":"371f5643d159a9daec925add0dc795f3e90be32c4d5c9b3ebc5d3a2428793c3f"},"schema_version":"1.0","source":{"id":"1705.04304","kind":"arxiv","version":3}},"canonical_sha256":"b2ceec4628f41817b0daf9ce778c831bec53387b42875695f9e67c56d0468bc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2ceec4628f41817b0daf9ce778c831bec53387b42875695f9e67c56d0468bc4","first_computed_at":"2026-05-18T00:30:44.866246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:44.866246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7luZHhi+jxMuGff+HYINWI/PrdOO2GoQ/OStloLUd4VzZJ9H3aBcEJs3Zj+4KFvPVdelCYpAK6cM+IH3ToCwBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:44.866870Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.04304","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5750b7fc00f718f377a4ef55f8fe173b5742bf05c5f8fc4ef8eb3ca16b8148dc","sha256:d1d0846bc17290a00cc8911812bb25d710e1cd7af1d153e87754752c0fd7ef73"],"state_sha256":"bf62bf979487c3c917608a967cf93d37aca8c2fb5182abb98de4fa33b40f6d67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJ/s59e70RYeRFx1SaGmrwmtP34y8eITMy5pjOLC5iSEnIfbTpfGVx8H+EX58GgwiQBjUBkZD5dXecXegc5ZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T10:40:55.317728Z","bundle_sha256":"27760d205a640a43693c6e837d2b7a0048eeaa69905ea3e61fcc89dfb0e128b4"}}