{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:E4TT4WAUHSUYA23I6SJ7SZUZ6N","short_pith_number":"pith:E4TT4WAU","canonical_record":{"source":{"id":"1805.00063","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T19:10:43Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"7423b2777697f9e83da0c9fb5900e07aaad06840ef91284124807de8c91b30da","abstract_canon_sha256":"a9e2dbd4790084011aaaf9fcf6c563f317c9ae682e0c0a12dda6642d03f50c61"},"schema_version":"1.0"},"canonical_sha256":"27273e58143ca9806b68f493f96699f353a31cfe64b03b6a9b1aa270814a7557","source":{"kind":"arxiv","id":"1805.00063","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00063","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00063v3","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00063","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"E4TT4WAUHSUY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"E4TT4WAUHSUYA23I","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"E4TT4WAU","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:E4TT4WAUHSUYA23I6SJ7SZUZ6N","target":"record","payload":{"canonical_record":{"source":{"id":"1805.00063","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T19:10:43Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"7423b2777697f9e83da0c9fb5900e07aaad06840ef91284124807de8c91b30da","abstract_canon_sha256":"a9e2dbd4790084011aaaf9fcf6c563f317c9ae682e0c0a12dda6642d03f50c61"},"schema_version":"1.0"},"canonical_sha256":"27273e58143ca9806b68f493f96699f353a31cfe64b03b6a9b1aa270814a7557","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:00.197566Z","signature_b64":"iYWNyw4PmIIXsdSSO/p/tsTNbiwPJ6nx7C0yzrtlZqg7Tt747XHsIeSenRp4MlizRnJOMSodomaFbpydt3nfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27273e58143ca9806b68f493f96699f353a31cfe64b03b6a9b1aa270814a7557","last_reissued_at":"2026-05-17T23:44:00.197053Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:00.197053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.00063","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":"2026-05-17T23:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLj3tPEKE1Zzc/PO4kcLYcsyd7eUYJ5sTvPEzqGMnVjl22GSCVUJUHA1cCYYNKqTN8g4thGTvVq0CaioCSHFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:22:33.775739Z"},"content_sha256":"043fbc13ddf87ec3ea7ffc0b47c231d7ef8facd2f958429d9c8816a41e4a52cb","schema_version":"1.0","event_id":"sha256:043fbc13ddf87ec3ea7ffc0b47c231d7ef8facd2f958429d9c8816a41e4a52cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:E4TT4WAUHSUYA23I6SJ7SZUZ6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Semantic Alignment for Improved Image Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Igor Melnyk, Jarret Ross, Pierre L. Dognin, Tom Sercu (IBM Research, USA), Youssef Mroueh","submitted_at":"2018-04-30T19:10:43Z","abstract_excerpt":"In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions. We empirically focus on the viability of two training methods: Self-critical Sequence Training (SCST) and Gumbel Straight-Through (ST) and demonstrate that SCST shows more stable gradient behavior and improved results over Gumbel ST, even without accessing discriminator gradients directly. We also address the problem of automatic evaluation for captioning models and introduce a new sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00063","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":"2026-05-17T23:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6bGNuiJf012gjVqobAYLZpq62dXnuSF9RE8G5OQniwZU30RmIAsugXIMkMBf21jOzlwULgv9yzXJulh1SmxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:22:33.776131Z"},"content_sha256":"c9cea9650095103fbf1229e276e48d3e444508c72a796a3156dd95eea4dd6da0","schema_version":"1.0","event_id":"sha256:c9cea9650095103fbf1229e276e48d3e444508c72a796a3156dd95eea4dd6da0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N/bundle.json","state_url":"https://pith.science/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N/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":"2026-05-27T01:22:33Z","links":{"resolver":"https://pith.science/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N","bundle":"https://pith.science/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N/bundle.json","state":"https://pith.science/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4TT4WAUHSUYA23I6SJ7SZUZ6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:E4TT4WAUHSUYA23I6SJ7SZUZ6N","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":"a9e2dbd4790084011aaaf9fcf6c563f317c9ae682e0c0a12dda6642d03f50c61","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T19:10:43Z","title_canon_sha256":"7423b2777697f9e83da0c9fb5900e07aaad06840ef91284124807de8c91b30da"},"schema_version":"1.0","source":{"id":"1805.00063","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00063","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00063v3","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00063","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"E4TT4WAUHSUY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"E4TT4WAUHSUYA23I","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"E4TT4WAU","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:c9cea9650095103fbf1229e276e48d3e444508c72a796a3156dd95eea4dd6da0","target":"graph","created_at":"2026-05-17T23:44:00Z","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":"In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions. We empirically focus on the viability of two training methods: Self-critical Sequence Training (SCST) and Gumbel Straight-Through (ST) and demonstrate that SCST shows more stable gradient behavior and improved results over Gumbel ST, even without accessing discriminator gradients directly. We also address the problem of automatic evaluation for captioning models and introduce a new sem","authors_text":"Igor Melnyk, Jarret Ross, Pierre L. Dognin, Tom Sercu (IBM Research, USA), Youssef Mroueh","cross_cats":["cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T19:10:43Z","title":"Adversarial Semantic Alignment for Improved Image Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00063","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":"sha256:043fbc13ddf87ec3ea7ffc0b47c231d7ef8facd2f958429d9c8816a41e4a52cb","target":"record","created_at":"2026-05-17T23:44:00Z","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":"a9e2dbd4790084011aaaf9fcf6c563f317c9ae682e0c0a12dda6642d03f50c61","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-30T19:10:43Z","title_canon_sha256":"7423b2777697f9e83da0c9fb5900e07aaad06840ef91284124807de8c91b30da"},"schema_version":"1.0","source":{"id":"1805.00063","kind":"arxiv","version":3}},"canonical_sha256":"27273e58143ca9806b68f493f96699f353a31cfe64b03b6a9b1aa270814a7557","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27273e58143ca9806b68f493f96699f353a31cfe64b03b6a9b1aa270814a7557","first_computed_at":"2026-05-17T23:44:00.197053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:00.197053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iYWNyw4PmIIXsdSSO/p/tsTNbiwPJ6nx7C0yzrtlZqg7Tt747XHsIeSenRp4MlizRnJOMSodomaFbpydt3nfBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:00.197566Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.00063","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:043fbc13ddf87ec3ea7ffc0b47c231d7ef8facd2f958429d9c8816a41e4a52cb","sha256:c9cea9650095103fbf1229e276e48d3e444508c72a796a3156dd95eea4dd6da0"],"state_sha256":"e5d6672fb9a7fae0033c316bf090860b296086af33e2c0007fcc4f03439f6700"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CVucgFMmuVPd9Uyowlr7x3AlWgCpJJktum03jnV6vVvpOQWxdhp3E442twEDDGocNC7sJQU6irKvsN6G3doACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:22:33.780132Z","bundle_sha256":"6edca4954a9fba4c0d97b3e36747477cda9fd45ccbe27820fc5a6721f85c1f7f"}}