{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BYJDF3ZYHA5NRWNDHBVPIDG3HT","short_pith_number":"pith:BYJDF3ZY","canonical_record":{"source":{"id":"1608.05813","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-20T12:12:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6eb3f35847366650f90ce74f811357d660e239e653d69e8948ec5337e08cee3c","abstract_canon_sha256":"5bcff82b91a0fb2f85c6cdb0e69d857de26518e2a02a56be63be0e0c2550408b"},"schema_version":"1.0"},"canonical_sha256":"0e1232ef38383ad8d9a3386af40cdb3cdeee80ec94b13d00bbc69b985cb6012e","source":{"kind":"arxiv","id":"1608.05813","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05813","created_at":"2026-05-18T00:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05813v5","created_at":"2026-05-18T00:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05813","created_at":"2026-05-18T00:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"BYJDF3ZYHA5N","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"BYJDF3ZYHA5NRWND","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"BYJDF3ZY","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BYJDF3ZYHA5NRWNDHBVPIDG3HT","target":"record","payload":{"canonical_record":{"source":{"id":"1608.05813","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-20T12:12:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6eb3f35847366650f90ce74f811357d660e239e653d69e8948ec5337e08cee3c","abstract_canon_sha256":"5bcff82b91a0fb2f85c6cdb0e69d857de26518e2a02a56be63be0e0c2550408b"},"schema_version":"1.0"},"canonical_sha256":"0e1232ef38383ad8d9a3386af40cdb3cdeee80ec94b13d00bbc69b985cb6012e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:59.100014Z","signature_b64":"pSqKf2UYv7C7AByFxrpjtyvA+KXjdShcNZakuCzt23X+fag/wc5+tzyyJ+54ac99F/neQ3N0iqfRghw6/zP+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1232ef38383ad8d9a3386af40cdb3cdeee80ec94b13d00bbc69b985cb6012e","last_reissued_at":"2026-05-18T00:31:59.099537Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:59.099537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.05813","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzNS/64dXa77OwwiTZwR8QCrwf3vC4YVPE21PLmPhOddclMnXEO+Qb8SNlFD711s3n7s2oaXjy41AIoE68DWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T00:48:44.349358Z"},"content_sha256":"93b949d2090d5151a2d4c5af560086865ca447666a6dccb306dfaf0bcf513121","schema_version":"1.0","event_id":"sha256:93b949d2090d5151a2d4c5af560086865ca447666a6dccb306dfaf0bcf513121"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BYJDF3ZYHA5NRWNDHBVPIDG3HT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Chee Seng Chan, Ying Hua Tan","submitted_at":"2016-08-20T12:12:09Z","abstract_excerpt":"A picture is worth a thousand words. Not until recently, however, we noticed some success stories in understanding of visual scenes: a model that is able to detect/name objects, describe their attributes, and recognize their relationships/interactions. In this paper, we propose a phrase-based hierarchical Long Short-Term Memory (phi-LSTM) model to generate image description. The proposed model encodes sentence as a sequence of combination of phrases and words, instead of a sequence of words alone as in those conventional solutions. The two levels of this model are dedicated to i) learn to gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05813","kind":"arxiv","version":5},"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":"2026-05-18T00:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ma+23G65pSvfw2UeD6pNI5CZwFJvRm8fIXPA8v0Nb5OCrIWOB392CYabJh/vwDVExrvy/Cn/pyJdk4tpcE7FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T00:48:44.350031Z"},"content_sha256":"c6f71b4b0ab5d50e95c247c1097b4a9e59c074d39740650d5a12cffc014dafe9","schema_version":"1.0","event_id":"sha256:c6f71b4b0ab5d50e95c247c1097b4a9e59c074d39740650d5a12cffc014dafe9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT/bundle.json","state_url":"https://pith.science/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT/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":"2026-05-23T00:48:44Z","links":{"resolver":"https://pith.science/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT","bundle":"https://pith.science/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT/bundle.json","state":"https://pith.science/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYJDF3ZYHA5NRWNDHBVPIDG3HT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BYJDF3ZYHA5NRWNDHBVPIDG3HT","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":"5bcff82b91a0fb2f85c6cdb0e69d857de26518e2a02a56be63be0e0c2550408b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-20T12:12:09Z","title_canon_sha256":"6eb3f35847366650f90ce74f811357d660e239e653d69e8948ec5337e08cee3c"},"schema_version":"1.0","source":{"id":"1608.05813","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05813","created_at":"2026-05-18T00:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05813v5","created_at":"2026-05-18T00:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05813","created_at":"2026-05-18T00:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"BYJDF3ZYHA5N","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"BYJDF3ZYHA5NRWND","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"BYJDF3ZY","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:c6f71b4b0ab5d50e95c247c1097b4a9e59c074d39740650d5a12cffc014dafe9","target":"graph","created_at":"2026-05-18T00:31:59Z","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":"A picture is worth a thousand words. Not until recently, however, we noticed some success stories in understanding of visual scenes: a model that is able to detect/name objects, describe their attributes, and recognize their relationships/interactions. In this paper, we propose a phrase-based hierarchical Long Short-Term Memory (phi-LSTM) model to generate image description. The proposed model encodes sentence as a sequence of combination of phrases and words, instead of a sequence of words alone as in those conventional solutions. The two levels of this model are dedicated to i) learn to gene","authors_text":"Chee Seng Chan, Ying Hua Tan","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-20T12:12:09Z","title":"phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05813","kind":"arxiv","version":5},"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":"sha256:93b949d2090d5151a2d4c5af560086865ca447666a6dccb306dfaf0bcf513121","target":"record","created_at":"2026-05-18T00:31:59Z","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":"5bcff82b91a0fb2f85c6cdb0e69d857de26518e2a02a56be63be0e0c2550408b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-20T12:12:09Z","title_canon_sha256":"6eb3f35847366650f90ce74f811357d660e239e653d69e8948ec5337e08cee3c"},"schema_version":"1.0","source":{"id":"1608.05813","kind":"arxiv","version":5}},"canonical_sha256":"0e1232ef38383ad8d9a3386af40cdb3cdeee80ec94b13d00bbc69b985cb6012e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e1232ef38383ad8d9a3386af40cdb3cdeee80ec94b13d00bbc69b985cb6012e","first_computed_at":"2026-05-18T00:31:59.099537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:59.099537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pSqKf2UYv7C7AByFxrpjtyvA+KXjdShcNZakuCzt23X+fag/wc5+tzyyJ+54ac99F/neQ3N0iqfRghw6/zP+CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:59.100014Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.05813","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93b949d2090d5151a2d4c5af560086865ca447666a6dccb306dfaf0bcf513121","sha256:c6f71b4b0ab5d50e95c247c1097b4a9e59c074d39740650d5a12cffc014dafe9"],"state_sha256":"48e767f26e0e8017e5af8a26db9cf46afd2b8f5aaa7f8967419e757d3a1f2482"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJwsCTXjo1EOAlYH17nyFvOw85YmOcxpCzekVXfU5rHgI4IgMg+C3fevtm7o+ubdar73dM2CZSbCv/tjyxvIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T00:48:44.352948Z","bundle_sha256":"9e1d091bef16bcf4f698263676ca61f42bf3e61d6f2664f111d570a22c27b14b"}}