{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZCI3T763IRECYKJ2743GANX2CQ","short_pith_number":"pith:ZCI3T763","canonical_record":{"source":{"id":"1703.02710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T05:24:52Z","cross_cats_sorted":[],"title_canon_sha256":"e48446eac643e58507f41a343a8514baab835aeb535539e3d7c689fc646d0a57","abstract_canon_sha256":"5b82c076e27cc790538b889ca95f672f017b2faf2ee89798ab763c3abb934a4e"},"schema_version":"1.0"},"canonical_sha256":"c891b9ffdb44482c293aff366036fa142d53f76daa8439668ea770a0b0432eb5","source":{"kind":"arxiv","id":"1703.02710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.02710","created_at":"2026-05-18T00:49:05Z"},{"alias_kind":"arxiv_version","alias_value":"1703.02710v1","created_at":"2026-05-18T00:49:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02710","created_at":"2026-05-18T00:49:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZCI3T763IREC","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZCI3T763IRECYKJ2","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZCI3T763","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZCI3T763IRECYKJ2743GANX2CQ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.02710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T05:24:52Z","cross_cats_sorted":[],"title_canon_sha256":"e48446eac643e58507f41a343a8514baab835aeb535539e3d7c689fc646d0a57","abstract_canon_sha256":"5b82c076e27cc790538b889ca95f672f017b2faf2ee89798ab763c3abb934a4e"},"schema_version":"1.0"},"canonical_sha256":"c891b9ffdb44482c293aff366036fa142d53f76daa8439668ea770a0b0432eb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:05.814463Z","signature_b64":"46qwf7dnkGYLrRnNqADrt3q12oavR00bSY/YbGQr3H0fHTyTspDZHcilaCZHOzAp9a2m+dhPVS2AKh8Tgg4VBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c891b9ffdb44482c293aff366036fa142d53f76daa8439668ea770a0b0432eb5","last_reissued_at":"2026-05-18T00:49:05.813955Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:05.813955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.02710","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":"2026-05-18T00:49:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6/j+UCfGqKFxZyJKpLRAF6034xsmlALd8KVr6SH9GK7ZMhJllnVFbGQyIJ+SYnShuAD96BgVGyY39UYxnyzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T15:47:39.632335Z"},"content_sha256":"e3cd4d414e32997607bd938bc998d36fdda1d519288d7eff35353c8c454c6b47","schema_version":"1.0","event_id":"sha256:e3cd4d414e32997607bd938bc998d36fdda1d519288d7eff35353c8c454c6b47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZCI3T763IRECYKJ2743GANX2CQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tree-Structured Reinforcement Learning for Sequential Object Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashi Feng, Shuicheng Yan, Wen Feng Lu, Xiaodan Liang, Xiaojie Jin, Zequn Jie","submitted_at":"2017-03-08T05:24:52Z","abstract_excerpt":"Existing object proposal algorithms usually search for possible object regions over multiple locations and scales separately, which ignore the interdependency among different objects and deviate from the human perception procedure. To incorporate global interdependency between objects into object localization, we propose an effective Tree-structured Reinforcement Learning (Tree-RL) approach to sequentially search for objects by fully exploiting both the current observation and historical search paths. The Tree-RL approach learns multiple searching policies through maximizing the long-term rewa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02710","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":"2026-05-18T00:49:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sh14KunIKzc5hcvKMrkIA81PjfU2zemyRAWd9KiPn8vZmc8Q2HFzYHBGYKomMZGLkmntPvdRN96wq8EZBwbsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T15:47:39.632679Z"},"content_sha256":"51b66b4e676369dda13d94923c95326581a35786db35d173907f50aa8ef0a04c","schema_version":"1.0","event_id":"sha256:51b66b4e676369dda13d94923c95326581a35786db35d173907f50aa8ef0a04c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCI3T763IRECYKJ2743GANX2CQ/bundle.json","state_url":"https://pith.science/pith/ZCI3T763IRECYKJ2743GANX2CQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCI3T763IRECYKJ2743GANX2CQ/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":"2026-05-20T15:47:39Z","links":{"resolver":"https://pith.science/pith/ZCI3T763IRECYKJ2743GANX2CQ","bundle":"https://pith.science/pith/ZCI3T763IRECYKJ2743GANX2CQ/bundle.json","state":"https://pith.science/pith/ZCI3T763IRECYKJ2743GANX2CQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCI3T763IRECYKJ2743GANX2CQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZCI3T763IRECYKJ2743GANX2CQ","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":"5b82c076e27cc790538b889ca95f672f017b2faf2ee89798ab763c3abb934a4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T05:24:52Z","title_canon_sha256":"e48446eac643e58507f41a343a8514baab835aeb535539e3d7c689fc646d0a57"},"schema_version":"1.0","source":{"id":"1703.02710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.02710","created_at":"2026-05-18T00:49:05Z"},{"alias_kind":"arxiv_version","alias_value":"1703.02710v1","created_at":"2026-05-18T00:49:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02710","created_at":"2026-05-18T00:49:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZCI3T763IREC","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZCI3T763IRECYKJ2","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZCI3T763","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:51b66b4e676369dda13d94923c95326581a35786db35d173907f50aa8ef0a04c","target":"graph","created_at":"2026-05-18T00:49:05Z","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":"Existing object proposal algorithms usually search for possible object regions over multiple locations and scales separately, which ignore the interdependency among different objects and deviate from the human perception procedure. To incorporate global interdependency between objects into object localization, we propose an effective Tree-structured Reinforcement Learning (Tree-RL) approach to sequentially search for objects by fully exploiting both the current observation and historical search paths. The Tree-RL approach learns multiple searching policies through maximizing the long-term rewa","authors_text":"Jiashi Feng, Shuicheng Yan, Wen Feng Lu, Xiaodan Liang, Xiaojie Jin, Zequn Jie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T05:24:52Z","title":"Tree-Structured Reinforcement Learning for Sequential Object Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02710","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:e3cd4d414e32997607bd938bc998d36fdda1d519288d7eff35353c8c454c6b47","target":"record","created_at":"2026-05-18T00:49:05Z","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":"5b82c076e27cc790538b889ca95f672f017b2faf2ee89798ab763c3abb934a4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T05:24:52Z","title_canon_sha256":"e48446eac643e58507f41a343a8514baab835aeb535539e3d7c689fc646d0a57"},"schema_version":"1.0","source":{"id":"1703.02710","kind":"arxiv","version":1}},"canonical_sha256":"c891b9ffdb44482c293aff366036fa142d53f76daa8439668ea770a0b0432eb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c891b9ffdb44482c293aff366036fa142d53f76daa8439668ea770a0b0432eb5","first_computed_at":"2026-05-18T00:49:05.813955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:05.813955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46qwf7dnkGYLrRnNqADrt3q12oavR00bSY/YbGQr3H0fHTyTspDZHcilaCZHOzAp9a2m+dhPVS2AKh8Tgg4VBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:05.814463Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.02710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3cd4d414e32997607bd938bc998d36fdda1d519288d7eff35353c8c454c6b47","sha256:51b66b4e676369dda13d94923c95326581a35786db35d173907f50aa8ef0a04c"],"state_sha256":"1c3a52f1768450b92c5626882ece6dfcb128a056a69046faeef560c81d481e02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6LeWAcWFhq8WVnf8BNDZjQu4wUaqTX9GR1YoBxuO3Il7SjyRPxJq4rE7QOGlMgwYwVEhqeWP+aP10Hi55G82Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T15:47:39.634579Z","bundle_sha256":"23a942ec9037ab030417dfb1bb2857b0d303f5db59b0971f8775c23b04af75eb"}}