{"abstract":"end marker is expanded as an ordinary live token.","category":"Beam search bookkeeping","checks":6,"contract":"Children are [parent,token,score]; tokens equal eos complete a path. Return (live,finished) lists preserving child rows.","contract_signature":"children, eos","evaluation_group":"beam-terminal_routing","failed_approach":"Dropping every end-marker child loses valid completed hypotheses.","family":"w3-beam-search-bookkeeping-terminal-routing","id":"FA-98461","implementations":{"attempt":{"sha256":"b73bb1e011eb5408e367d60a81c87b1837a84d677006d4742faa69b3a898ca74","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(children, eos):\n    return ([r for r in children if r[1]!=eos],[])\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\nc=[[0,'x',N],[0,'END',N+1],[1,'y',N-1]]\ncheck('live and done',solve(c,'END'),([c[0],c[2]],[c[1]]))\ncheck('all terminal',solve([[0,'END',N]],'END'),([] ,[[0,'END',N]]))\ncheck('no terminal',solve([[0,'x',N]],'END'),([[0,'x',N]],[]))\ncheck('empty children',solve([],'END'),([],[]))\ncheck('multiple completions',solve([[0,'END',1],[1,'END',2]],'END'),([] ,[[0,'END',1],[1,'END',2]]))\ncheck('token N remains live',solve([[0,N,N+1]],'END'),([[0,N,N+1]],[]))\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"},"broken":{"sha256":"c93bcf383baf121193379bcecd9dedd11dac8cfce7464ec9c02ef6e81347a347","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(children, eos):\n    return (list(children),[])\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\nc=[[0,'x',N],[0,'END',N+1],[1,'y',N-1]]\ncheck('live and done',solve(c,'END'),([c[0],c[2]],[c[1]]))\ncheck('all terminal',solve([[0,'END',N]],'END'),([] ,[[0,'END',N]]))\ncheck('no terminal',solve([[0,'x',N]],'END'),([[0,'x',N]],[]))\ncheck('empty children',solve([],'END'),([],[]))\ncheck('multiple completions',solve([[0,'END',1],[1,'END',2]],'END'),([] ,[[0,'END',1],[1,'END',2]]))\ncheck('token N remains live',solve([[0,N,N+1]],'END'),([[0,N,N+1]],[]))\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"}},"limitations":"This is a finite toy beam-state contract and makes no claim about neural model quality or production decoding. This reproducer isolates one failure mechanism. Results cover the supplied fixtures. Variants within a family share a test contract and should remain grouped when constructing evaluation splits. Related mechanisms with a shared evaluation_group must also remain together; these controlled models are not independent production incidents.","method":"Deterministic executable model with adversarial boundary fixtures.","provenance":{"created_by":"Failure Map","dependencies":"Python standard library","family":"w3-beam-search-bookkeeping-terminal-routing","generated_at":"2026-09-30T16:48:13.239438+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"Beam decoders rely on consistent hypothesis state while expanding and ranking candidates.","root_cause":"A completed hypothesis remains in the active set and receives further tokens.","sha256":"0541b821294a850f7af99b0e1104df6933e767a9c4b371d2fff54395b21ee0f1","title":"Beam search: end marker is expanded as an ordinary live token · case 01","variant":1,"variant_policy":"The fixture code references N, supplied as 1 through 5. Fixed boundary checks may repeat. These records share one mechanism and must remain together in evaluation splits.","verified":true,"visibility":"public","verification":{"attempt":{"elapsed_ms":28.41,"exit_code":1,"observations":[{"actual":[[[0,"x",1],[1,"y",0]],[]],"check":"live and done","expected":[[[0,"x",1],[1,"y",0]],[[0,"END",2]]],"passed":false},{"actual":[[],[]],"check":"all terminal","expected":[[],[[0,"END",1]]],"passed":false},{"actual":[[[0,"x",1]],[]],"check":"no terminal","expected":[[[0,"x",1]],[]],"passed":true},{"actual":[[],[]],"check":"empty children","expected":[[],[]],"passed":true},{"actual":[[],[]],"check":"multiple completions","expected":[[],[[0,"END",1],[1,"END",2]]],"passed":false},{"actual":[[[0,1,2]],[]],"check":"token N remains live","expected":[[[0,1,2]],[]],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"live and done\", \"actual\": [[[0, \"x\", 1], [1, \"y\", 0]], []], \"expected\": [[[0, \"x\", 1], [1, \"y\", 0]], [[0, \"END\", 2]]], \"passed\": false}, {\"check\": \"all terminal\", \"actual\": [[], []], \"expected\": [[], [[0, \"END\", 1]]], \"passed\": false}, {\"check\": \"no terminal\", \"actual\": [[[0, \"x\", 1]], []], \"expected\": [[[0, \"x\", 1]], []], \"passed\": true}, {\"check\": \"empty children\", \"actual\": [[], []], \"expected\": [[], []], \"passed\": true}, {\"check\": \"multiple completions\", \"actual\": [[], []], \"expected\": [[], [[0, \"END\", 1], [1, \"END\", 2]]], \"passed\": false}, {\"check\": \"token N remains live\", \"actual\": [[[0, 1, 2]], []], \"expected\": [[[0, 1, 2]], []], \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":25.898,"exit_code":1,"observations":[{"actual":[[[0,"x",1],[0,"END",2],[1,"y",0]],[]],"check":"live and done","expected":[[[0,"x",1],[1,"y",0]],[[0,"END",2]]],"passed":false},{"actual":[[[0,"END",1]],[]],"check":"all terminal","expected":[[],[[0,"END",1]]],"passed":false},{"actual":[[[0,"x",1]],[]],"check":"no terminal","expected":[[[0,"x",1]],[]],"passed":true},{"actual":[[],[]],"check":"empty children","expected":[[],[]],"passed":true},{"actual":[[[0,"END",1],[1,"END",2]],[]],"check":"multiple completions","expected":[[],[[0,"END",1],[1,"END",2]]],"passed":false},{"actual":[[[0,1,2]],[]],"check":"token N remains live","expected":[[[0,1,2]],[]],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"live and done\", \"actual\": [[[0, \"x\", 1], [0, \"END\", 2], [1, \"y\", 0]], []], \"expected\": [[[0, \"x\", 1], [1, \"y\", 0]], [[0, \"END\", 2]]], \"passed\": false}, {\"check\": \"all terminal\", \"actual\": [[[0, \"END\", 1]], []], \"expected\": [[], [[0, \"END\", 1]]], \"passed\": false}, {\"check\": \"no terminal\", \"actual\": [[[0, \"x\", 1]], []], \"expected\": [[[0, \"x\", 1]], []], \"passed\": true}, {\"check\": \"empty children\", \"actual\": [[], []], \"expected\": [[], []], \"passed\": true}, {\"check\": \"multiple completions\", \"actual\": [[[0, \"END\", 1], [1, \"END\", 2]], []], \"expected\": [[], [[0, \"END\", 1], [1, \"END\", 2]]], \"passed\": false}, {\"check\": \"token N remains live\", \"actual\": [[[0, 1, 2]], []], \"expected\": [[[0, 1, 2]], []], \"passed\": true}], \"passed\": false}\n"}},"member_only":{"stages":["fixed"],"fields":["implementations.fixed","verification.fixed","harness","repair"],"note":"The verified repair, its recorded checks, the repair description, and the scoring harness are available to members."}}