{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Q4WQKATRMWSJ7NROXSJSUYC5K2","short_pith_number":"pith:Q4WQKATR","canonical_record":{"source":{"id":"1805.03616","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T16:56:41Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ce1a5cced9126657d5902b0c9cb35d92fd5cca15d94602dba53b8700b1ed7558","abstract_canon_sha256":"d187bc6c49b0ebbfa3328d0b5fdb6f018157cc7c0ad752aa43a594a2152faa54"},"schema_version":"1.0"},"canonical_sha256":"872d05027165a49fb62ebc932a605d56909b0a5815f327071a281b885a4eadbc","source":{"kind":"arxiv","id":"1805.03616","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03616","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03616v3","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03616","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"Q4WQKATRMWSJ","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"Q4WQKATRMWSJ7NRO","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"Q4WQKATR","created_at":"2026-07-05T01:22:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Q4WQKATRMWSJ7NROXSJSUYC5K2","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03616","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T16:56:41Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ce1a5cced9126657d5902b0c9cb35d92fd5cca15d94602dba53b8700b1ed7558","abstract_canon_sha256":"d187bc6c49b0ebbfa3328d0b5fdb6f018157cc7c0ad752aa43a594a2152faa54"},"schema_version":"1.0"},"canonical_sha256":"872d05027165a49fb62ebc932a605d56909b0a5815f327071a281b885a4eadbc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:13.207168Z","signature_b64":"5hZj0tQ1AvjRWOaleswI6FVyNndsSVyYOFCPlGv6Jx43BG2fu124lWHl4DRLwZFNmAgGfBspwsNsE6dudnX8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872d05027165a49fb62ebc932a605d56909b0a5815f327071a281b885a4eadbc","last_reissued_at":"2026-07-05T01:22:13.206721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:13.206721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03616","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":"2026-07-05T01:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9m2uE0VTmuJxWbSnoPZcKguco3Hj3xEE0+2LiNj6pwxpQ0ZOyEmkgSZaZ99aifCRcDl1yHolcXgJ7rfgLzSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:32:20.870385Z"},"content_sha256":"937699a9b514be5d251ad72ebe580801e460366fcb36b780d53719df1ad26cb9","schema_version":"1.0","event_id":"sha256:937699a9b514be5d251ad72ebe580801e460366fcb36b780d53719df1ad26cb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Q4WQKATRMWSJ7NROXSJSUYC5K2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Junlin Yao, Li Wang, Li Zhong, Qiang Du, Wei Liu, Yunzhe Tao","submitted_at":"2018-05-09T16:56:41Z","abstract_excerpt":"In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03616","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1805.03616/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":"2026-07-05T01:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPMQYi7IBU6CdKqZBioBxzQe1PpycGbE+JnV28UBQsScx4ECcinx6hWxNogDw650SbX7kwGqLTs2f+Leb3WZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:32:20.870906Z"},"content_sha256":"a4d48bd30222dd839468d074e0d98838e5da017e506ec77f1c02706b151bfd2b","schema_version":"1.0","event_id":"sha256:a4d48bd30222dd839468d074e0d98838e5da017e506ec77f1c02706b151bfd2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2/bundle.json","state_url":"https://pith.science/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2/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":"2026-08-10T09:32:20Z","links":{"resolver":"https://pith.science/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2","bundle":"https://pith.science/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2/bundle.json","state":"https://pith.science/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4WQKATRMWSJ7NROXSJSUYC5K2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Q4WQKATRMWSJ7NROXSJSUYC5K2","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":"d187bc6c49b0ebbfa3328d0b5fdb6f018157cc7c0ad752aa43a594a2152faa54","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T16:56:41Z","title_canon_sha256":"ce1a5cced9126657d5902b0c9cb35d92fd5cca15d94602dba53b8700b1ed7558"},"schema_version":"1.0","source":{"id":"1805.03616","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03616","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03616v3","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03616","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"Q4WQKATRMWSJ","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"Q4WQKATRMWSJ7NRO","created_at":"2026-07-05T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"Q4WQKATR","created_at":"2026-07-05T01:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:a4d48bd30222dd839468d074e0d98838e5da017e506ec77f1c02706b151bfd2b","target":"graph","created_at":"2026-07-05T01:22:13Z","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/1805.03616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE,","authors_text":"Junlin Yao, Li Wang, Li Zhong, Qiang Du, Wei Liu, Yunzhe Tao","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T16:56:41Z","title":"A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03616","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":"sha256:937699a9b514be5d251ad72ebe580801e460366fcb36b780d53719df1ad26cb9","target":"record","created_at":"2026-07-05T01:22:13Z","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":"d187bc6c49b0ebbfa3328d0b5fdb6f018157cc7c0ad752aa43a594a2152faa54","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T16:56:41Z","title_canon_sha256":"ce1a5cced9126657d5902b0c9cb35d92fd5cca15d94602dba53b8700b1ed7558"},"schema_version":"1.0","source":{"id":"1805.03616","kind":"arxiv","version":3}},"canonical_sha256":"872d05027165a49fb62ebc932a605d56909b0a5815f327071a281b885a4eadbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"872d05027165a49fb62ebc932a605d56909b0a5815f327071a281b885a4eadbc","first_computed_at":"2026-07-05T01:22:13.206721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:22:13.206721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5hZj0tQ1AvjRWOaleswI6FVyNndsSVyYOFCPlGv6Jx43BG2fu124lWHl4DRLwZFNmAgGfBspwsNsE6dudnX8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:22:13.207168Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03616","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:937699a9b514be5d251ad72ebe580801e460366fcb36b780d53719df1ad26cb9","sha256:a4d48bd30222dd839468d074e0d98838e5da017e506ec77f1c02706b151bfd2b"],"state_sha256":"0d38e9f644d1dbf42e59d64ee189c0f3d79d7113cb734fcb414882b5b7013085"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCutm8q/6PXMZUK2ShGtGrBYB87Gs3BwPlhwBZid8pSkn6/RrGUuQNR/4i9V0sY2bxzzuelFxPWnnHMi897HDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:32:20.875808Z","bundle_sha256":"f2057e9343ab25926773b84daa5b997809b606a664975a09e354ecc3c2699923"}}