{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:46FAPSPPRHGKFKHU44CA5GZPNG","short_pith_number":"pith:46FAPSPP","canonical_record":{"source":{"id":"1604.01904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-07T07:47:11Z","cross_cats_sorted":[],"title_canon_sha256":"0e16e2388a25ee7b0d5c3081a68983f7a424e110f46e6374da13c5c0831a3a90","abstract_canon_sha256":"294fa90d756c4b1ff6b1072d8594752d72cd4ae02024a663d67b6b2b9402f407"},"schema_version":"1.0"},"canonical_sha256":"e78a07c9ef89cca2a8f4e7040e9b2f698fa229571f4cb56517167e86fcb32cc7","source":{"kind":"arxiv","id":"1604.01904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.01904","created_at":"2026-05-18T01:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"1604.01904v2","created_at":"2026-05-18T01:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01904","created_at":"2026-05-18T01:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"46FAPSPPRHGK","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"46FAPSPPRHGKFKHU","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"46FAPSPP","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:46FAPSPPRHGKFKHU44CA5GZPNG","target":"record","payload":{"canonical_record":{"source":{"id":"1604.01904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-07T07:47:11Z","cross_cats_sorted":[],"title_canon_sha256":"0e16e2388a25ee7b0d5c3081a68983f7a424e110f46e6374da13c5c0831a3a90","abstract_canon_sha256":"294fa90d756c4b1ff6b1072d8594752d72cd4ae02024a663d67b6b2b9402f407"},"schema_version":"1.0"},"canonical_sha256":"e78a07c9ef89cca2a8f4e7040e9b2f698fa229571f4cb56517167e86fcb32cc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:52.275920Z","signature_b64":"nZz9pl6TDJjorLStAOwkQZtitbQEtAfenyWIpCHIGWzzcCxdGhGstQyE605jHRBsW1V9v1QPcB77r0JZjCYAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78a07c9ef89cca2a8f4e7040e9b2f698fa229571f4cb56517167e86fcb32cc7","last_reissued_at":"2026-05-18T01:02:52.275423Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:52.275423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.01904","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":"2026-05-18T01:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UiRXlO9E+hTyhv6Xn8XqxBGF3WVqTVRPcZH9KoSElc+2aOXR7eUVXmkPw3ijKFMfXbKECLLUNSChNTSdeD85Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:51:25.039234Z"},"content_sha256":"f3b06f132c391ae8955891befad62c5940460a7cfee99a1aba13bf04b5197c7c","schema_version":"1.0","event_id":"sha256:f3b06f132c391ae8955891befad62c5940460a7cfee99a1aba13bf04b5197c7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:46FAPSPPRHGKFKHU44CA5GZPNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Headline Generation with Sentence-wise Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayana, Maosong Sun, Shiqi Shen, Yu Zhao, Zhiyuan Liu","submitted_at":"2016-04-07T07:47:11Z","abstract_excerpt":"Recently, neural models have been proposed for headline generation by learning to map documents to headlines with recurrent neural networks. Nevertheless, as traditional neural network utilizes maximum likelihood estimation for parameter optimization, it essentially constrains the expected training objective within word level rather than sentence level. Moreover, the performance of model prediction significantly relies on training data distribution. To overcome these drawbacks, we employ minimum risk training strategy in this paper, which directly optimizes model parameters in sentence level w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01904","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":""},"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":"2026-05-18T01:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNCXIFKRDKi/uhM+pNJabM5ZYGcy66Q3oX1kIy3QyJvl9JGFZBCxn5d+/hR4zywCKD3uFtCOJzOKVP/s0zwWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:51:25.039830Z"},"content_sha256":"ea75e994f8b881bbda4f7007842df2c84dfa6cebf3dcc8dd97759795d250885f","schema_version":"1.0","event_id":"sha256:ea75e994f8b881bbda4f7007842df2c84dfa6cebf3dcc8dd97759795d250885f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46FAPSPPRHGKFKHU44CA5GZPNG/bundle.json","state_url":"https://pith.science/pith/46FAPSPPRHGKFKHU44CA5GZPNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46FAPSPPRHGKFKHU44CA5GZPNG/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":"2026-06-03T08:51:25Z","links":{"resolver":"https://pith.science/pith/46FAPSPPRHGKFKHU44CA5GZPNG","bundle":"https://pith.science/pith/46FAPSPPRHGKFKHU44CA5GZPNG/bundle.json","state":"https://pith.science/pith/46FAPSPPRHGKFKHU44CA5GZPNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46FAPSPPRHGKFKHU44CA5GZPNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:46FAPSPPRHGKFKHU44CA5GZPNG","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":"294fa90d756c4b1ff6b1072d8594752d72cd4ae02024a663d67b6b2b9402f407","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-07T07:47:11Z","title_canon_sha256":"0e16e2388a25ee7b0d5c3081a68983f7a424e110f46e6374da13c5c0831a3a90"},"schema_version":"1.0","source":{"id":"1604.01904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.01904","created_at":"2026-05-18T01:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"1604.01904v2","created_at":"2026-05-18T01:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01904","created_at":"2026-05-18T01:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"46FAPSPPRHGK","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"46FAPSPPRHGKFKHU","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"46FAPSPP","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:ea75e994f8b881bbda4f7007842df2c84dfa6cebf3dcc8dd97759795d250885f","target":"graph","created_at":"2026-05-18T01:02:52Z","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":"Recently, neural models have been proposed for headline generation by learning to map documents to headlines with recurrent neural networks. Nevertheless, as traditional neural network utilizes maximum likelihood estimation for parameter optimization, it essentially constrains the expected training objective within word level rather than sentence level. Moreover, the performance of model prediction significantly relies on training data distribution. To overcome these drawbacks, we employ minimum risk training strategy in this paper, which directly optimizes model parameters in sentence level w","authors_text":"Ayana, Maosong Sun, Shiqi Shen, Yu Zhao, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-07T07:47:11Z","title":"Neural Headline Generation with Sentence-wise Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01904","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:f3b06f132c391ae8955891befad62c5940460a7cfee99a1aba13bf04b5197c7c","target":"record","created_at":"2026-05-18T01:02:52Z","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":"294fa90d756c4b1ff6b1072d8594752d72cd4ae02024a663d67b6b2b9402f407","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-07T07:47:11Z","title_canon_sha256":"0e16e2388a25ee7b0d5c3081a68983f7a424e110f46e6374da13c5c0831a3a90"},"schema_version":"1.0","source":{"id":"1604.01904","kind":"arxiv","version":2}},"canonical_sha256":"e78a07c9ef89cca2a8f4e7040e9b2f698fa229571f4cb56517167e86fcb32cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e78a07c9ef89cca2a8f4e7040e9b2f698fa229571f4cb56517167e86fcb32cc7","first_computed_at":"2026-05-18T01:02:52.275423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:02:52.275423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nZz9pl6TDJjorLStAOwkQZtitbQEtAfenyWIpCHIGWzzcCxdGhGstQyE605jHRBsW1V9v1QPcB77r0JZjCYAAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:02:52.275920Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.01904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3b06f132c391ae8955891befad62c5940460a7cfee99a1aba13bf04b5197c7c","sha256:ea75e994f8b881bbda4f7007842df2c84dfa6cebf3dcc8dd97759795d250885f"],"state_sha256":"563e1434eed0b33febf75c4fda5d84c7bb860acc83eb77924bef79b0f6d3e017"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScZ80oM73JFtZot4gqIizJCYmw0Sw9GWCcmhbeT/gSqHzJiJRdD/zfBYYBLRQ3eJkEmBgMx8NUmWnLONFFfWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:51:25.043067Z","bundle_sha256":"17ac7aab96b868b0010c910192c12e91bb58065ca93ccfeae36cb8b636bca268"}}