{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IFLYV3KN6AWJ7M5QUTB6WV2CJO","short_pith_number":"pith:IFLYV3KN","canonical_record":{"source":{"id":"1706.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-05T08:09:20Z","cross_cats_sorted":[],"title_canon_sha256":"84432001498816a14c9c8739a4bf0c5dcea727f10b9481296372004785b488ed","abstract_canon_sha256":"359bd76d4bec8a4ad3e06908d21912ff1f41a9a7ac1374f73b1a313c6b00b4d0"},"schema_version":"1.0"},"canonical_sha256":"41578aed4df02c9fb3b0a4c3eb57424b8348b725782ecc6e10700e9e7fa5c13b","source":{"kind":"arxiv","id":"1706.01231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01231","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01231v1","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01231","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"IFLYV3KN6AWJ","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IFLYV3KN6AWJ7M5Q","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IFLYV3KN","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IFLYV3KN6AWJ7M5QUTB6WV2CJO","target":"record","payload":{"canonical_record":{"source":{"id":"1706.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-05T08:09:20Z","cross_cats_sorted":[],"title_canon_sha256":"84432001498816a14c9c8739a4bf0c5dcea727f10b9481296372004785b488ed","abstract_canon_sha256":"359bd76d4bec8a4ad3e06908d21912ff1f41a9a7ac1374f73b1a313c6b00b4d0"},"schema_version":"1.0"},"canonical_sha256":"41578aed4df02c9fb3b0a4c3eb57424b8348b725782ecc6e10700e9e7fa5c13b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:04.089938Z","signature_b64":"L7fUtR69qOquHokmLD0FDmTB5cTuHy4AqsAXknqUH6IuuS+Qf/SFV+B/LW7wRvWJMFp8Obqfi/llujgbIJ4EDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41578aed4df02c9fb3b0a4c3eb57424b8348b725782ecc6e10700e9e7fa5c13b","last_reissued_at":"2026-05-18T00:43:04.089269Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:04.089269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.01231","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEBjrJ+V1RMPcOzRvNoguO1S0yAlJGv4qlgW7BMukd3HGRJARR3i6edO4Vtt2RA6S9wWuf12W1uuYtQptoRgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:31:24.410817Z"},"content_sha256":"7a02f2f85f000b2dd5014aaf65af6d49cde81c1eea31fc7b1483b268f0a4696f","schema_version":"1.0","event_id":"sha256:7a02f2f85f000b2dd5014aaf65af6d49cde81c1eea31fc7b1483b268f0a4696f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IFLYV3KN6AWJ7M5QUTB6WV2CJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical LSTM with Adjusted Temporal Attention for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongxiang Zhang, Heng Tao Shen, Jingkuan Song, Lianli Gao, Wu Liu, Zhao Guo","submitted_at":"2017-06-05T08:09:20Z","abstract_excerpt":"Recent progress has been made in using attention based encoder-decoder framework for video captioning. However, most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., \"gun\" and \"shooting\") and non-visual words (e.g. \"the\", \"a\"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of video captioning. To address this issue, we propose a hierarchical LSTM with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01231","kind":"arxiv","version":1},"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":"2026-05-18T00:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CQmB44/DbPC/O14Jn20ZwsMMLXaKpi+dq2wsQuYhOyxcKvzNrImdj2c3pPCkunV3mUts4JBLoIoEEJxYRqpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:31:24.411192Z"},"content_sha256":"79d114fe4b48e5c7e6680c30ebb12a7fde8b95986c91c55bd6ad0dbcaeb6bc07","schema_version":"1.0","event_id":"sha256:79d114fe4b48e5c7e6680c30ebb12a7fde8b95986c91c55bd6ad0dbcaeb6bc07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO/bundle.json","state_url":"https://pith.science/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO/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":"2026-05-31T07:31:24Z","links":{"resolver":"https://pith.science/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO","bundle":"https://pith.science/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO/bundle.json","state":"https://pith.science/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFLYV3KN6AWJ7M5QUTB6WV2CJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IFLYV3KN6AWJ7M5QUTB6WV2CJO","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":"359bd76d4bec8a4ad3e06908d21912ff1f41a9a7ac1374f73b1a313c6b00b4d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-05T08:09:20Z","title_canon_sha256":"84432001498816a14c9c8739a4bf0c5dcea727f10b9481296372004785b488ed"},"schema_version":"1.0","source":{"id":"1706.01231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01231","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01231v1","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01231","created_at":"2026-05-18T00:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"IFLYV3KN6AWJ","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IFLYV3KN6AWJ7M5Q","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IFLYV3KN","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:79d114fe4b48e5c7e6680c30ebb12a7fde8b95986c91c55bd6ad0dbcaeb6bc07","target":"graph","created_at":"2026-05-18T00:43:04Z","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":"Recent progress has been made in using attention based encoder-decoder framework for video captioning. However, most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., \"gun\" and \"shooting\") and non-visual words (e.g. \"the\", \"a\"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of video captioning. To address this issue, we propose a hierarchical LSTM with ","authors_text":"Dongxiang Zhang, Heng Tao Shen, Jingkuan Song, Lianli Gao, Wu Liu, Zhao Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-05T08:09:20Z","title":"Hierarchical LSTM with Adjusted Temporal Attention for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01231","kind":"arxiv","version":1},"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":"sha256:7a02f2f85f000b2dd5014aaf65af6d49cde81c1eea31fc7b1483b268f0a4696f","target":"record","created_at":"2026-05-18T00:43:04Z","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":"359bd76d4bec8a4ad3e06908d21912ff1f41a9a7ac1374f73b1a313c6b00b4d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-05T08:09:20Z","title_canon_sha256":"84432001498816a14c9c8739a4bf0c5dcea727f10b9481296372004785b488ed"},"schema_version":"1.0","source":{"id":"1706.01231","kind":"arxiv","version":1}},"canonical_sha256":"41578aed4df02c9fb3b0a4c3eb57424b8348b725782ecc6e10700e9e7fa5c13b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41578aed4df02c9fb3b0a4c3eb57424b8348b725782ecc6e10700e9e7fa5c13b","first_computed_at":"2026-05-18T00:43:04.089269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:04.089269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L7fUtR69qOquHokmLD0FDmTB5cTuHy4AqsAXknqUH6IuuS+Qf/SFV+B/LW7wRvWJMFp8Obqfi/llujgbIJ4EDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:04.089938Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.01231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a02f2f85f000b2dd5014aaf65af6d49cde81c1eea31fc7b1483b268f0a4696f","sha256:79d114fe4b48e5c7e6680c30ebb12a7fde8b95986c91c55bd6ad0dbcaeb6bc07"],"state_sha256":"18ed41bf558c29a6bb6f5954485df043bba5797042075fd87bf4f65a00754422"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20BAYI9BZrYrH3bNGAM5Xi8Wzdtun4Cpa5Gwfty4Kyw3NcKiTOogUWDjhGk2oDLL+f6+pE9rbmv3ia7/2AjRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:31:24.413622Z","bundle_sha256":"cd6ec0f9d86ca28cd7fcf9cf63cda5fa8ba1f75b15fe501ff0043d6f07dc7263"}}